docs: 修复论文 OCR markdown 图片路径，添加 33 张提取图片
- GRAB: 11 张图片（imgs/grab/） - HSTU: 22 张图片（imgs/hstu/） - 图片路径从 imgs/ 改为 imgs/grab/ 和 imgs/hstu/
This commit is contained in:
+313
-294
@@ -18,7 +18,8 @@ Departing from the structural constraints of DLRMs, the rise of Large Language M
|
||||
|
||||
Despite these theoretical advancements, deploying GR models in high-throughput industrial systems remains challenging due to strict online serving and optimization constraints. The primary obstacle is computational efficiency. Standard Transformer training requires extensive padding for variable-length sequences, resulting in significant computational waste (Vaswani et al., 2017; Krell et al., 2021). While the sequence packing—a common Natural Language Processing (NLP) technique for concatenating multiple short sequences—effectively mitigates this issue (Krell et al., 2021), its straightforward application to recommendation systems triggers a more subtle yet damaging failure mode: Distribution Skew (Baylor et al., 2017; Polyzotis et al., 2019; Sculley et al., 2015; Han et al., 2025).
|
||||
|
||||
In recommendations, packing a user's full history creates mini-batches with excessive intra-user correlation, which violates the i.i.d. assumption typically relied on by SGD-style optimization (Doan et al., 2020). This skew (details in Appendix D.1) causes sparse parameters (i.e., embedding tables) to overfit specific users, hindering the generalization of dense parameters (e.g., Transformer weights responsible for inference) (Naumov et al., 2019; Li et al., 2024b). This reveals a fundamental tension: sparse parameters require diverse, uncorrelated samples for robust “memorization”, whereas dense parameters benefit from long, coherent contexts for sequential “reasoning” (Cheng et al., 2016; Kang & McAuley, 2018; Sun et al., 2019). This misalignment implies that standard synchronous training on packed sequences may lead to suboptimal convergence due to the conflicting gradient requirements of the sparse and dense components (Yu et al., 2020).
|
||||
In recommendations, packing a user's full history creates mini-batches with excessive intra-user correlation, which violates the i.i.d. assumption typically relied on by SGD-
|
||||
style optimization (Doan et al., 2020). This skew (details in Appendix D.1) causes sparse parameters (i.e., embedding tables) to overfit specific users, hindering the generalization of dense parameters (e.g., Transformer weights responsible for inference) (Naumov et al., 2019; Li et al., 2024b). This reveals a fundamental tension: sparse parameters require diverse, uncorrelated samples for robust “memorization”, whereas dense parameters benefit from long, coherent contexts for sequential “reasoning” (Cheng et al., 2016; Kang & McAuley, 2018; Sun et al., 2019). This misalignment implies that standard synchronous training on packed sequences may lead to suboptimal convergence due to the conflicting gradient requirements of the sparse and dense components (Yu et al., 2020).
|
||||
|
||||
Meanwhile, existing GR models typically ignore data heterogeneity, resulting in performance limitations (see Appendix A.3 for detailed discussion). To overcome these challenges, we propose Generative Ranking for Ads at Baidu (GRAB), an end-to-end sequential training and inference framework for industrial-grade CTR prediction. GRAB introduces three core innovations to reconcile the demands for performance, efficiency, and training stability:
|
||||
|
||||
@@ -42,290 +43,8 @@ GR. Recent GR work models recommendation as causal Transformer-based sequential
|
||||
|
||||
#### 3.1. DLRMs
|
||||
|
||||
The traditional DLRM architecture, as shown in Fig. 1, follows a modular processing pipeline for CTR prediction, handling raw features from users, candidate ads, and contextual signals. The pipeline involves: (a) expanding categorical features into fixed fields via feature engineering, (b) mapping these fields through hashing to obtain discrete ID vectors for embedding lookup in a Sparse Parameter Server Table (PSTable), and (c) concatenating and normalizing the retrieved embeddings to form a fixed-length flattened vector. This unified representation is then fed into an MLP, typically enhanced with a gating network, to model high-orderfeature interactions and generate the final CTR prediction.
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/img_in_image_box_190_187_498_411.jpg" alt="Image" width="25%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 1. The traditional DLRM architecture: sparse features are hashed to IDs and embedded via PSTable, and then concatenated into a fixed-length flattened vector for CTR prediction.</div>
|
||||
|
||||
|
||||
#### 3.2. Overall Architecture of GRAB
|
||||
|
||||
GRAB, with the overall architecture shown in Fig. 2, is designed to model user behavior history sequences in an end-to-end manner, as applied in scenarios like CTR prediction. GRAB follows a three-stage pipeline: (i) sparse feature layer; (ii) dense tokenizer; and (iii) sequence modeling layer. Given raw behavior logs, GRAB first converts heterogeneous categorical signals into sparse IDs at the event level, then tokenizes each event into a dense representation, and finally applies a sequence model to estimate the click probability of candidate ads. GRAB uses its dense representation calculated from the dense tokenizer to bridge DLRM-style sparse feature engineering and GR-style sequential modeling, enabling end-to-end training and inference along a single, unified computation path from input to output, thereby improving CTR prediction performance through end-to-end sequential modeling of event-level user behaviors.
|
||||
|
||||
Sparse Feature Layer. The sparse feature layer (details in Appendix C.1) processes raw logs into time-ordered event sequences. Each event's categorical fields are converted into sparse IDs using standard DLRM feature engineering (Section 3.1), yielding a structured sequence of events annotated with field-wise IDs.
|
||||
|
||||
Dense Tokenizer. Unlike DLRM, which collapses field embeddings into a fixed-length, order-agnostic vector for pointwise processing, GRAB preserves the temporal event structure. It aggregates per-event field embeddings and projects them into $ \mathbb{R}^{d_{model}} $ to form sequential event tokens (Appendix C.2), resulting in a time-ordered token sequence. This sequence serves as the input to a subsequent Transformer, thereby enabling the modeling of long-range dependencies and interest drift.
|
||||
|
||||
Autoregressive-like Sequence Modeling Layer. Built on sequence packing (Section 3.3.1), heterogeneous tokens (Section 3.3.2), and action-aware relative attention bias (Section 3.3.3), our core contribution is the CamA mechanism (Section 3.3.4). CamA integrates a multi-channel design for parallel processing of diverse behaviors and inherits action-aware contextualization from RAB, providing a unified and efficient framework for modeling complex user interest patterns across scenarios.
|
||||
|
||||
|
||||
|
||||
#### 3.3. Autoregressive-like Sequence Modeling Layer
|
||||
|
||||
Following the dense tokenizer, this layer is designed to capture the temporal dependencies and dynamic evolution of user interests, which takes the sequence of dense event tokens generated by the preceding layer as input (as described in Appendix C.3). Formally, for a user $ u $, the input sequence consists of the behavior history $ \mathbf{E}^{\mathrm{beh}} = \{e_t^{\mathrm{beh}}\}_{t=1}^T $ and the candidate advertisements $ \mathbf{E}^{\mathrm{ad}} = \{e_i^{\mathrm{ad}}\}_{i=1}^N_u $, where $ \mathbf{e}_t^{\mathrm{beh}}, \mathbf{e}_i^{\mathrm{ad}} \in \mathbb{R}^{d_{\mathrm{model}}} $ are the dense embeddings of the $ t $-th behavior event and the $ i $-th candidate ad, respectively, $ T_u $ is the behavior history length, and $ N_u $ is the number of candidate ads.
|
||||
|
||||
##### 3.3.1. SEQUENCE PACKING AND USER-ISOLATED CAUSAL MASK
|
||||
|
||||
In industrial training logs, as shown in the left image of Fig. 3a., a mini-batch is typically formed by sampling $ B_{ins} $ impression instances. Each instance contains a variable-length token sequence composed of (i) a subsequence of the user's historical behavior tokens and (ii) target advertisement tokens to be scored. A straightforward batching strategy pads every instance to a fixed length $ L_{max} $, yielding a dense tensor with dimensions $ B_{ins} \times L_{max} \times d_{model} $,
|
||||
|
||||
which introduces substantial computational waste when most instances are much shorter than $ L_{max} $.
|
||||
|
||||
To eliminate such padding overhead while preserving the temporal semantics, GRAB performs sequence packing by grouping tokens by user. Specifically, tokens from multiple impression instances belonging to the same user u are merged into a single contiguous token segment, while segments of different users are strictly separated. Within each user segment, all tokens are stably sorted by timestamp so that the packed segment forms a single timeline for sequential modeling. After packing, the batch is represented as one long packed tensor $ H = \text{Pack}(\mathbf{E}^{beh}, \mathbf{E}^{ad}) \in \mathbb{R}^{1 \times L \times d_{model}} $, where $ L $ denotes the total packed length across all users in the mini-batch.
|
||||
|
||||
For convenience, we associate each packed position $ p \in \{1, \ldots, L\} $ with (i) a segment $ id \sigma(p) \in U_B $ indicating which user it belongs to, and (ii) a local time index $ \ell(p) \in \{1, \ldots, L_{\sigma(p)}\} $ within that user segment.
|
||||
|
||||
User-isolated causal mask. On the packed tensor $ H $, we construct an additive attention mask $ M^{\text{pack}} \in \mathbb{R}^{L \times L} $ that<div style="text-align: center;"><img src="imgs/img_in_image_box_218_138_976_460.jpg" alt="Image" width="61%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 2. Overview of GRAB's end-to-end CTR prediction pipeline: (1) Tokenizing raw fields via a sparse PSTable and fusing them into event tokens. (2) Packing tokens per user with causal and heterogeneous masks. (3) Processing through N Transformer layers equipped with the Causal Action-aware Multi-channel Attention (CamA) mechanism. (4) Final CTR prediction from the output representations.</div>
|
||||
|
||||
|
||||
enforces two constraints: (1) user isolation (no cross-user attention), and (2) causality within each user's timeline (no future leakage). Formally, for query position p and key position q,
|
||||
|
||||
$$ M_{p,q}^{\mathrm{pack}}=\begin{cases}1,&if\sigma(p)=\sigma(q)and\ell(q)\leq\ell(p),\\0,&otherwise.\end{cases} $$
|
||||
|
||||
This yields a block-diagonal lower-triangular structure (as shown in Fig. 3b), where each block corresponds to one user segment.
|
||||
|
||||
##### 3.3.2. HETEROGENEOUS BEHAVIOR TOKENS AND HETEROGENEOUS VISIBILITY MASK
|
||||
|
||||
After sequence packing, for each user $u$, we obtain a user-isolated, time-ordered packed stream with its causal mask $M_{\text{pack}}$. To further reduce redundancy in the packed history while preserving the information needed for scoring the current candidate, we instantiate two token views at each packed timestamp $t$: the partial token (history) $h_t \in \mathbb{R}^{d_{\text{model}}}$, which retains only time-varying information that is useful for representing history and discards static or highly repetitive fields (e.g., user_id) that would otherwise be duplicated across historical steps and could lead to overfitting; and the full token (candidate) $h'_t \in \mathbb{R}^{d_{\text{model}}}$, which retains the complete information required to score the candidate at time $t$, including the static fields omitted from the partial history view. We then interleave them to form the heterogeneous packed sequence: $H_u = [\mathbf{h}_1, \mathbf{h}_1', \mathbf{h}_2, \mathbf{h}_2', \ldots, \mathbf{h}_{T_u}, \mathbf{h}_{T_u}']$.
|
||||
|
||||
Heterogeneous Visibility Mask. On top of the user-isolated causal constraint encoded by $ M^{pack} $, we apply a mask-rewriting operator $ \mathcal{R}(\cdot) $ to obtain the heterogeneous visibility mask $ M^{het} $. Concretely, $ \mathcal{R}(\cdot) $ rewrites the visibility pattern according to the token types in the following way: (i) partial $ (\mathcal{P}) $ tokens only attend to partial history tokens; and (ii) full $ (\mathcal{F}) $ tokens attend to partial history tokens and themselves, but never attend to other full tokens. Formally, index positions in $ H_u $ by $ n \in \{1, \ldots, 2T_u\} $, we define the time index $ \tau(n) = \lceil n/2 \rceil $ and token type $ \kappa(n) = \mathcal{P} $ if $ n $ is odd, otherwise $ \kappa(n) = \mathcal{F} $. Then the heterogeneous mask (as shown in Fig. 4) is
|
||||
|
||||
|
||||
|
||||
$$ M_{p,q}^{\mathrm{h e t}}=\begin{cases}{1,}&{\kappa(p)=\mathcal{P},\;\kappa(q)=\mathcal{P},\;\tau(q)\leq\tau(p),}\\ {1,}&{\kappa(p)=\mathcal{F},\;\kappa(q)=\mathcal{P},\;\tau(q)\leq\tau(p),}\\ {1,}&{\kappa(p)=\mathcal{F},\;p=q,}\\ {0,}&{\mathrm{o t h e r w i s e}.}\\ \end{cases} $$
|
||||
|
||||
##### 3.3.3. ACTION-AWARE ATTENTION: RELATIVE ENCODING AND EFFICIENT COMPUTATION
|
||||
|
||||
On top of the heterogeneous behavior tokens and the heterogeneous visibility mask $ M^{het} $, we further adopt a action-aware RAB(i.e., relative attention bias) causal attention mechanism. It augments standard multi-head self-attention with three designs: a causal mask to prevent future leakage, a dual sliding-window visibility constraint to support streaming-style training, and a query-aware relative bias that enables the query to directly interact with relative position/time/action signals.
|
||||
|
||||
Action-aware relative attention logits. Given a query $ q_{i} $ and a key $ k_{j} $, the attention logit is computed as
|
||||
|
||||
$$ w_{i,j}=\boldsymbol{q}_{i}^{\top}\cdot\left(k_{j}+P o s_{i,j}+A c t i o n_{i,j}+T i m e_{i,j}\right), $$
|
||||
|
||||
where $ Pos_{i,j} $, $ Action_{i,j} $, and $ Time_{i,j} $ are learnable embeddings derived from relative position, relative action, and relative time, respectively. For continuous or large-range<div style="text-align: center;"><img src="imgs/img_in_image_box_117_147_1083_497.jpg" alt="Image" width="78%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(a) Sequence Packing</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(b) User-isolated Causal Mask</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 3. Sequence packing and user-isolated causal masking in GRAB. (a) Instead of padding each impression instance to a fixed length $ L_{max} $, tokens from multiple impressions are concatenated within each user and different users are kept in disjoint segments, yielding a single packed sequence of length $ N_{token} $ for compute-efficient batching. (b) The user-isolated causal mask exhibits a block-diagonal lower-triangular pattern, so each token can only attend to past tokens within the same user segment, enforcing both user isolation and temporal causality.</div>
|
||||
|
||||
|
||||
signals (e.g., action statistics or play durations), we first discretize them into buckets and then perform embedding lookup.
|
||||
|
||||
Compared with a query-agnostic relative bias (e.g., $ w_{i,j} = q_i^\top k_j + Pos_{i,j} + \cdots $), Eq. 3 makes the relative signals action-aware via the interaction $ q_i^\top Pos_{i,j} $, $ q_i^\top Action_{i,j} $, and $ q_i^\top Time_{i,j} $, allowing the model to adaptively emphasize different contextual relations under different queries (i.e., target ads).
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/img_in_image_box_246_907_444_1138.jpg" alt="Image" width="16%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 4. Heterogeneous behavior tokens and heterogeneous visibility mask $ M^{het} $ (blue entries). Partial tokens attend only to partial-history tokens up to the current time, while full tokens attend to partial-history tokens up to their time index and to themselves, but never to other full tokens, preventing duplicated static information from propagating along time.</div>
|
||||
|
||||
|
||||
Causal mask with dual sliding windows. We enforce causality and further restrict attention using combined time and length windows. The mask is defined as $ M_{p,q}^{\text{rab}} = 1 $ if $ q \leq p $ and the distance p - q does not exceed the length sliding-window limit $ L_w $; otherwise $ M_{p,q}^{\text{rab}} = 0 $.
|
||||
|
||||
This serves two key industrial purposes: (1) it bounds per-token computation, guaranteeing stable throughput/latency over growing behavior histories; (2) it matches the online training paradigm—events arrive incrementally, and the model updates attention context on the fly without reprocessing the full sequence, boosting training efficiency and serving practicality.
|
||||
|
||||
|
||||
|
||||
Efficient computation. The naive implementation of Eq. 3 would yield an $ O(L^2d_{\text{model}}) $ intermediate tensor, which is prohibitively memory-intensive in practice. We adopt the optimization in (Golovneva et al., 2024) to re-order the computation. We define codebooks $ B^{\text{pos/act/time}} \in \mathbb{R}^{N_s \times d_{\text{model}}} $ and bucketized indices $ p_{i,j}, a_{i,j}, t_{i,j} $. Then Eq. 3 can be equivalently written as:
|
||||
|
||||
$$ w_{i,j}=q_{i}^{\top}k_{j}+(s_{i}^{p o s})[p_{i,j}]+(s_{i}^{a c t})[a_{i,j}]+(s_{i}^{t i m e})[t_{i,j}]. $$
|
||||
|
||||
where $ s_{i}^{\mathrm{pos}} = q_{i}^{\top}B^{\mathrm{pos}} $, $ s_{i}^{\mathrm{act}} = q_{i}^{\top}B^{\mathrm{act}} $, and $ s_{i}^{\mathrm{time}} = q_{i}^{\top}B^{\mathrm{time}} $. In practice, we first compute the projection vectors $ s_{i}^{*} $, then obtain relative terms via fast gather operations. This completely avoids the large $ L \times L \times d_{model} $ tensor, dramatically reducing peak memory and improving computational efficiency.
|
||||
|
||||
##### 3.3.4. MULTI-CHANNEL ATTENTION
|
||||
|
||||
While the action-aware RAB attention (Section 3.3.3) enhances each individual attention logit with relative position/action/time signals, it still treats the packed stream as a single mixed sequence. However, in industrial logs, user behaviors are highly heterogeneous (e.g., spanning different time windows or encompassing different behavior types),<div style="text-align: center;"><img src="imgs/img_in_image_box_137_140_560_318.jpg" alt="Image" width="34%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 5. Action-aware relative attention bias (RAB) with efficient computation. Left: a causal mask with dual sliding windows, which limits each query to attend only to recent past tokens visible within the sliding-window. Right: the action-aware relative encoding pipeline: relative time, position, and action signals are bucketized (as needed), embedded, summed, and injected to the attention logits.</div>
|
||||
|
||||
|
||||
and different behavioral subsets often exhibit distinct temporal dynamics and predictive value. A straightforward design is to flatten all tokens into a single sequence and apply causal self-attention, yet this couples heterogeneous sources into one interaction graph and incurs a quadratic cost (e.g., $ O((n + m)^2) $ for two sources with lengths $ n $ and $ m $). To improve both modeling effectiveness and efficiency, we further introduce the Causal Action-aware Multi-channel Attention (CamA) mechanism, which integrates a multi-channel design, conceptually analogous to multi-head attention but with channel-specific visibility constraints. We therefore model each channel with an independent causal self-attention stack, and fuse the channel-wise representations via a lightweight gated mixing module. Let $ \mathcal{C} = \{1, \ldots, C\} $ denote the channel set. For each user, channel $ c $ provides a token sequence $ \mathbf{X}^{(c)} \in \mathbb{R}^{T_c \times d} $, and we append the shared target token $ X^{ad} \in \mathbb{R}^d $:
|
||||
|
||||
$$ \mathbf{S}^{(c)}=[\mathbf{X}^{(c)};\mathbf{x}^{\mathrm{t a r}}]\in\mathbb{R}^{(T_{c}+1)\times d},\qquad t^{\star}=T_{c}+1. $$
|
||||
|
||||
Each channel is equipped with its own causal visibility mask $ \mathbf{M}^{(c)} $, and is encoded independently:
|
||||
|
||||
$$ \begin{align*}\mathbf{H}^{(c,\ell+1)}&=\mathrm{Layer}_{\ell}^{(c)}\Big(\tilde{\mathbf{H}}^{(c,\ell)};\mathbf{M}^{(c)}\Big),\\\mathbf{H}^{(c,0)}&=\mathbf{S}^{(c)},\quad c\in\mathcal{C}.\end{align*} $$
|
||||
|
||||
Target-token gated mixing. To enable cross-channel information sharing while keeping computation lightweight, we perform mixing only on the target position $ t^* $ at each layer. The mixed representation $ \tilde{\mathbf{h}}^{(c,\ell)} $ is obtained by first computing channel-wise gating weights $ \beta^{(c,\ell)} $ and then aggregating information from all other channels:
|
||||
|
||||
$$ \tilde{\mathbf{h}}^{(c,\ell)}=\mathbf{h}^{(c,\ell)}+\sum_{i\in\mathcal{C}\backslash\{c\}}\beta^{(i,\ell)}\odot\mathbf{h}^{(i,\ell)}. $$
|
||||
|
||||
This updated representation replaces $ \mathbf{h}^{(c,\ell)} $ at position $ t^{*} $, forming the updated channel representation $ \tilde{\mathbf{H}}^{(c,\ell)} $ used in (6). Finally, the concatenated last-layer target representations from all channels are used for CTR prediction.
|
||||
|
||||
|
||||
|
||||
#### 3.4. Sequence Then Sparse Training
|
||||
|
||||
While sequence packing (Section 3.3.1) significantly enhances computational efficiency, it introduces a critical challenge: distribution skew. Since samples within a packed mini-batch belong to the same user, the high intra-user correlation leads to redundant updates for specific sparse IDs, causing the model to overfit to specific user-ad interactions, rather than learning generalizable patterns. To mitigate this, we propose the Sequence Then Sparse (STS) training paradigm (detailed discussions in Appendix D), a two-stage decoupled optimization strategy that balances long-range sequential modeling with robust sparse feature learning.
|
||||
|
||||
##### 3.4.1. STAGE I: SEQUENCE MODELING (SEQUENCE PHASE)
|
||||
|
||||
The first stage focuses on capturing the evolution of user interests and temporal dependencies. We perform end-to-end autoregressive-like learning on the packed user sequences Z, which include candidate tokens and their historical trajectories. In this phase, we optimize the dense tokenizer and the causal Transformer, while keeping the Sparse Embedding Table $ \Phi $ frozen. By freezing $ \Phi $, we stabilize the token space, forcing the Transformer to focus exclusively on the relational dynamics between events rather than over-memorizing specific ID features.
|
||||
|
||||
##### 3.4.2. STAGE II: SPARSE FEATURE LEARNING (SPARSE PHASE)
|
||||
|
||||
The second stage is designed to refine the discrete representations, particularly for long-tail IDs. In this phase, we revert to a non-sequential format, treating each sample as an independent user-ad exposure to break the distribution skewness. This stage optimizes the sparse embeddings $ \Phi $, which act as a robust corrector for the gradient accumulation amplified by sequence packing. It ensures that the basic feature representations remain accurate and unbiased across the entire traffic distribution.
|
||||
|
||||
### 4. System Deployment
|
||||
|
||||
GRAB has been successfully deployed in a large-scale feed ad ranking system, handling billions of daily requests. Unlike conventional memory-bound DLRMs, GR is markedly compute-bound due to the quadratic complexity of Transformer self-attention. To satisfy stringent latency requirements, we implemented a co-designed hardware-software architecture. Due to space constraints, we provide the comprehensive system overview (Fig. 8) and detailed deployment optimizations in Appendix E.### 5. Experiment
|
||||
|
||||
#### 5.1. Overall Performance Comparison
|
||||
|
||||
We first compared the performance of GRAB against state-of-the-art recommendation models on the Baidu real-world industrial dataset. The training data, derived from the Baidu real recommendation advertising scene, contains billions of users, exposure logs, and click logs. The test set includes millions of users, billions of exposure logs, and millions of click logs. The baselines encompass both DL-RMs and GR models, including: DIN (Zhou et al., 2018), which models short-term user behavior with target attention; SIM(Soft) (Pi et al., 2020), a sequential model that uses soft-search to encode user interests; TWIN (Si et al., 2024), which extends multi-head target attention from ESU to GSU; HSTU (Zhai et al., 2024), an efficient model for long-sequence behavior modeling; and LONGER (Chai et al., 2025), a Transformer-based architecture designed for ultra-long behavior sequences. Experimental results are presented in Table 1: GRAB outperforms all other baselines, achieving a 0.19% relative improvement over the most competitive model. Meanwhile, Fig. 6a illustrates the performance of different models across varying lengths of user behavior sequences. GRAB surpasses other recommendation models at all sequence lengths, with its performance gains becoming more pronounced as the sequence length increases.
|
||||
|
||||
<div style="text-align: center;">Table 1. Overall performance in industrial settings</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>AUC</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>DIN</td><td style='text-align: center; word-wrap: break-word;'>0.83309</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>SIM Soft</td><td style='text-align: center; word-wrap: break-word;'>0.83520</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>TWIN</td><td style='text-align: center; word-wrap: break-word;'>0.83556</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>HSTU</td><td style='text-align: center; word-wrap: break-word;'>0.83590</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>LONGER</td><td style='text-align: center; word-wrap: break-word;'>0.83615</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB-small</td><td style='text-align: center; word-wrap: break-word;'>0.83661</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB-standard</td><td style='text-align: center; word-wrap: break-word;'>0.83772</td></tr></table>
|
||||
|
||||
#### 5.2. Scaling Analysis
|
||||
|
||||
We evaluate model performance across different capacity scales by independently scaling the number of Transformer blocks( $ n_{layer} $), the number of attention heads( $ n_{head} $), and the feature dimension of the model( $ d_{model} $) in Table 2, Fig. 6b presents the test-set performance of the GRAB model under varying configurations (i.e., $ n_{layer} $, $ n_{head} $ and $ d_{model} $). These results demonstrate that increasing model capacity effectively improves model performance. We also found that as the model capacity increases, the performance improvement on longer user behavior sequences becomes more significant. Moreover, no significant saturation trend is observed within the current range of configurations, which also confirms the strong scalability of the GRAB model.
|
||||
|
||||
<div style="text-align: center;">Table 2. Comparison of models with different settings</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>Params</td><td style='text-align: center; word-wrap: break-word;'>Setting</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{2l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.51M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=2 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.67M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{6l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.83M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=6 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{2l-4h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.48M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=2 $, $ n_{head}=4 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.63M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-128d} $</td><td style='text-align: center; word-wrap: break-word;'>7.05M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=128 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-256d} $</td><td style='text-align: center; word-wrap: break-word;'>8.13M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=256 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-512d} $</td><td style='text-align: center; word-wrap: break-word;'>11.27M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=512 $</td></tr></table>
|
||||
|
||||
#### 5.3. Ablation Study
|
||||
|
||||
Heterogeneous Tokens. We conduct ablation studies on heterogeneous representations with three configurations: GRAB with heterogeneous, only partial, or only full tokens (Table 3). Results show that heterogeneous representations achieve the best performance. Using only partial tokens leads to significant degradation, confirming that full feature representations are more beneficial for target scoring. Notably, using only full tokens also degrades performance, suggesting that artificially designed statistical features can introduce confusion and impair sequence modeling.
|
||||
|
||||
<div style="text-align: center;">Table 3. Ablation studies of GRAB</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>AUC</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB</td><td style='text-align: center; word-wrap: break-word;'>0.83772</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/ Partial Token</td><td style='text-align: center; word-wrap: break-word;'>0.83492</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/ Full Token</td><td style='text-align: center; word-wrap: break-word;'>0.83749</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative pos</td><td style='text-align: center; word-wrap: break-word;'>0.83768</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative time</td><td style='text-align: center; word-wrap: break-word;'>0.83743</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative action</td><td style='text-align: center; word-wrap: break-word;'>0.83724</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o Multi-channel</td><td style='text-align: center; word-wrap: break-word;'>0.83743</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o Target-token mix</td><td style='text-align: center; word-wrap: break-word;'>0.83768</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB_sparse</td><td style='text-align: center; word-wrap: break-word;'>0.83614</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB_sparse w/o STS</td><td style='text-align: center; word-wrap: break-word;'>0.83549</td></tr></table>
|
||||
|
||||
Action-aware Attention. We ablate three components of GRAB's Action-aware Attention: relative position, time, and action. The results (Table 3) show that removing any of these components degrades performance. The decline is more pronounced for time and action than for position, indicating that historical sequences are more sensitive to behavioral and temporal signals. We also analyze the attention weight distribution across buckets defined by relative position/time differences (smaller values denote more recent tokens). As shown in Figure 7, weights decrease as bucket values increase, confirming that more recent behaviors better reflect user interest and receive higher weights. For relative action, we compare positive (click) and negative (non-click) labels. The weight distribution is highly skewed: positive labels account for 88% of the total weight, versus only 12%<div style="text-align: center;"><img src="imgs/img_in_chart_box_110_146_498_401.jpg" alt="Image" width="31%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(a) Overall Performance</div>
|
||||
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/img_in_chart_box_694_136_1079_398.jpg" alt="Image" width="31%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(b) Scaling Performance</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 6. DLRMs vs. GRs across different user behavior sequence lengths (a), with a +0.1% improvement in AUC, indicating a significant enhancement. GRABs comparison in different parameter scale(b)</div>
|
||||
|
||||
|
||||
for negative labels. This suggests that incorporating more positive feedback could further improve sequence modeling.
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/img_in_chart_box_172_627_504_881.jpg" alt="Image" width="27%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 7. The weight distribution of action-aware attention in relative position and relative time.</div>
|
||||
|
||||
|
||||
Multi-channel Attention. To verify the effectiveness of multi-channel attention in sequence modeling, we conduct the following settings: 1) the GRAB model without multi-channel attention, that is, using a single channel for sequence modeling, 2) remain the multi-channel attention and only remove the target token mix component. As shown in Table 3, both configurations have varying degrees of performance degradation, indicating that each component is indispensable. In terms of performance, multi-channel attention is crucial, and adding the target token mix component can further improve performance.
|
||||
|
||||
STS Training. We evaluate the STS paradigm by comparing GRAB's second-stage training with and without sequence modeling for sparse feature learning. With STS, sparse embeddings are updated through sequence modeling on packed user behavior sequences; without STS, the same batch data is treated as independent exposures. Results (as shown in Table 3) show that STS brings significant accuracy gains in sparse feature learning, confirming the efficacy of the two-stage training. This demonstrates that STS alleviates the distribution skew and overfitting caused by direct sequence-packed training.
|
||||
|
||||
|
||||
|
||||
#### 5.4. Online A/B Test
|
||||
|
||||
To assess the online performance of GRAB, we deployed it in Baidu home feed scenario of Baidu and compared its performance with the current online DLRM model. The experiment used 10% of the main traffic and remained online for about a month. Online evaluation shows that GRAB delivered 3.49% improvement in CTR and 3.05% improvement in CPM, which indicates that GRAB achieves more accurate advertising estimation and brings considerable revenue increments. Notably, GRAB has already been fully deployed on Baidu, and the online inference costs on par with the previous online DLRM model.
|
||||
|
||||
### 6. Conclusion
|
||||
|
||||
We propose GRAB, an end-to-end generative ranking framework that integrates a novel CamA mechanism to effectively capture temporal dynamics and specific action signals within user behavior sequences. On Baidu billion-scale industrial dataset, GRAB establishes a new state-of-the-art, outperforming DLRM and other GR baselines. Ablation studies validate the necessity of its key components, and our proposed STS training paradigm effectively mitigates distribution shift. Scaling analysis indicates continued gains from larger models and longer sequences. Finally, full online A/B testing in Baidu home feed ads shows that GRAB boosts CTR by 3.49% and CPM by 3.05%, leading to full production deployment. Further discussion of this work can be found in the Appendix F.## References
|
||||
|
||||
Agarwal, S., Yan, C., Zhang, Z., and Venkataraman, S. Bagpipe: Accelerating deep recommendation model training. In Proceedings of the 29th Symposium on Operating Systems Principles, pp. 348–363, 2023.
|
||||
|
||||
Bai, J., Geng, X., Deng, J., Xia, Z., Jiang, H., Yan, G., and Liang, J. A comprehensive survey on advertising click-through rate prediction algorithm. The Knowledge Engineering Review, 40:e3, 2025.
|
||||
|
||||
Bao, K., Zhang, J., Zhang, Y., Wang, W., Feng, F., and He, X. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In Proceedings of the 17th ACM conference on recommender systems, pp. 1007–1014, 2023.
|
||||
|
||||
Cao, Y., Mehta, N., Yi, X., Keshavan, R. H., Heldt, L., Hong, L., Chi, E., and Sathiamoorthy, M. Aligning large language models with recommendation knowledge. In Findings of the Association for Computational Linguistics: NAACL 2024, pp. 1051–1066, 2024.
|
||||
|
||||
Baylor, D., Breck, E., Cheng, H.-T., Fiedel, N., Foo, C. Y., Haque, Z., Haykal, S., Ispir, M., Jain, V., Koc, L., et al. Tfx: A tensorflow-based production-scale machine learning platform. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1387–1395, 2017.
|
||||
|
||||
Chai, Z., Ren, Q., Xiao, X., Yang, H., Han, B., Zhang, S., Chen, D., Lu, H., Zhao, W., Yu, L., et al. Longer: Scaling up long sequence modeling in industrial recommenders. In Proceedings of the Nineteenth ACM Conference on Recommender Systems, pp. 247–256, 2025.
|
||||
|
||||
Chen, J., Chi, L., Peng, B., and Yuan, Z. Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740, 2024.
|
||||
|
||||
Cheng, H.-T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., et al. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems, pp. 7–10, 2016.
|
||||
|
||||
Covington, P., Adams, J., and Sargin, E. Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM conference on recommender systems, pp. 191–198, 2016.
|
||||
|
||||
Di Palma, D., Biancofiore, G. M., Anelli, V. W., Narducci, F., Di Noia, T., and Di Sciascio, E. Evaluating chatgpt as a recommender system: A rigorous approach. arXiv preprint arXiv:2309.03613, 2023.
|
||||
|
||||
Doan, T. T., Nguyen, L. M., Pham, N. H., and Romberg, J. Finite-time analysis of stochastic gradient descent under markov randomness. arXiv preprint arXiv:2003.10973, 2020.
|
||||
|
||||
Geng, B., Huan, Z., Zhang, X., He, Y., Zhang, L., Yuan, F., Zhou, J., and Mo, L. Breaking the length barrier: Llm-enhanced ctr prediction in long textual user behaviors. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2311–2315, 2024.
|
||||
|
||||
Golovneva, O., Wang, T., Weston, J., and Sukhbaatar, S. Contextual position encoding: Learning to count what's important. arXiv preprint arXiv:2405.18719, 2024.
|
||||
|
||||
Guo, H., Tang, R., Ye, Y., Li, Z., and He, X. Deepfm: a factorization-machine based neural network for ctr prediction. arXiv preprint arXiv:1703.04247, 2017.
|
||||
|
||||
Han, R., Yin, B., Chen, S., Jiang, H., Jiang, F., Li, X., Ma, C., Huang, M., Li, X., Jing, C., et al. Mtgr: Industrial-scale generative recommendation framework in meituan. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pp. 5731–5738, 2025.
|
||||
|
||||
He, X., Pan, J., Jin, O., Xu, T., Liu, B., Xu, T., Shi, Y., Atallah, A., Herbrich, R., Bowers, S., et al. Practical lessons from predicting clicks on ads at facebook. In Proceedings of the eighth international workshop on data mining for online advertising, pp. 1–9, 2014.
|
||||
|
||||
He, Z., Xie, Z., Jha, R., Steck, H., Liang, D., Feng, Y., Majumder, B. P., Kallus, N., and McAuley, J. Large language models as zero-shot conversational recommenders. In Proceedings of the 32nd ACM international conference on information and knowledge management, pp. 720–730, 2023.
|
||||
|
||||
Hou, Y., Mu, S., Zhao, W. X., Li, Y., Ding, B., and Wen, J.-R. Towards universal sequence representation learning for recommender systems. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp. 585–593, 2022.
|
||||
|
||||
Hou, Y., He, Z., McAuley, J., and Zhao, W. X. Learning vector-quantized item representation for transferable sequential recommenders. In Proceedings of the ACM Web Conference 2023, pp. 1162–1171, 2023.
|
||||
|
||||
Jia, J., Wang, Y., Li, Y., Chen, H., Bai, X., Liu, Z., Liang, J., Chen, Q., Li, H., Jiang, P., et al. Learn: Knowledge adaptation from large language model to recommendation for practical industrial application. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pp. 11861–11869, 2025.Kang, W.-C. and McAuley, J. Self-attentive sequential recommendation. In 2018 IEEE international conference on data mining (ICDM), pp. 197–206. IEEE, 2018.
|
||||
|
||||
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020.
|
||||
|
||||
Krell, M. M., Kosec, M., Perez, S. P., and Fitzgibbon, A. Efficient sequence packing without cross-contamination: Accelerating large language models without impacting performance. arXiv preprint arXiv:2107.02027, 2021.
|
||||
|
||||
Li, L., Zhang, Y., Liu, D., and Chen, L. Large language models for generative recommendation: A survey and visionary discussions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 10146–10159, 2024a.
|
||||
|
||||
Li, R., Deng, W., Cheng, Y., Yuan, Z., Zhang, J., and Yuan, F. Exploring the upper limits of text-based collaborative filtering using large language models: Discoveries and insights. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pp. 1643–1653, 2025.
|
||||
|
||||
Li, S., Guo, H., Tang, X., Tang, R., Hou, L., Li, R., and Zhang, R. Embedding compression in recommender systems: A survey. ACM Computing Surveys, 56(5):1–21, 2024b.
|
||||
|
||||
Lin, J., Dai, X., Xi, Y., Liu, W., Chen, B., Zhang, H., Liu, Y., Wu, C., Li, X., Zhu, C., et al. How can recommender systems benefit from large language models: A survey. ACM Transactions on Information Systems, 43(2):1–47, 2025.
|
||||
|
||||
Lin, Z., Ding, H., Hoang, N. T., Kveton, B., Deoras, A., and Wang, H. Pre-trained recommender systems: A causal debiasing perspective. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 424–433, 2024.
|
||||
|
||||
Liu, J., Liu, C., Zhou, P., Lv, R., Zhou, K., and Zhang, Y. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149, 2023.
|
||||
|
||||
Luo, S., He, B., Zhao, H., Shao, W., Qi, Y., Huang, Y., Zhou, A., Yao, Y., Li, Z., Xiao, Y., et al. Recranker: Instruction tuning large language model as ranker for top-k recommendation. ACM Transactions on Information Systems, 43(5):1–31, 2025.
|
||||
|
||||
Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., and Chi, E. H. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th
|
||||
|
||||
ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1930–1939, 2018a.
|
||||
|
||||
Ma, X., Zhao, L., Huang, G., Wang, Z., Hu, Z., Zhu, X., and Gai, K. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1137–1140, 2018b.
|
||||
|
||||
Mudigere, D., Hao, Y., Huang, J., Jia, Z., Tulloch, A., Sridharan, S., Liu, X., Ozdal, M., Nie, J., Park, J., et al. Software-hardware co-design for fast and scalable training of deep learning recommendation models. In Proceedings of the 49th Annual International Symposium on Computer Architecture, pp. 993–1011, 2022.
|
||||
|
||||
Naumov, M., Mudigere, D., Shi, H.-J. M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C.-J., Azzolini, A. G., et al. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091, 2019.
|
||||
|
||||
Ning, L., Liu, L., Wu, J., Wu, N., Berlowitz, D., Prakash, S., Green, B., O'Banion, S., and Xie, J. User-llm: Efficient llm contextualization with user embeddings. In Companion Proceedings of the ACM on Web Conference 2025, pp. 1219–1223, 2025.
|
||||
|
||||
Petrov, A. V. and Macdonald, C. Generative sequential recommendation with gptrec. arXiv preprint arXiv:2306.11114, 2023.
|
||||
|
||||
Pi, Q., Bian, W., Zhou, G., Zhu, X., and Gai, K. Practice on long sequential user behavior modeling for click-through rate prediction. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 2671–2679, 2019.
|
||||
|
||||
Pi, Q., Zhou, G., Zhang, Y., Wang, Z., Ren, L., Fan, Y., Zhu, X., and Gai, K. Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2685–2692, 2020.
|
||||
|
||||
Polyzotis, N., Zinkevich, M., Roy, S., Breck, E., and Whang, S. Data validation for machine learning. Proceedings of machine learning and systems, 1:334–347, 2019.
|
||||
|
||||
Rajput, S., Mehta, N., Singh, A., Hulikal Keshavan, R., Vu, T., Heldt, L., Hong, L., Tay, Y., Tran, V., Samost, J., et al. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, 36: 10299–10315, 2023.Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., and Dennison, D. Hidden technical debt in machine learning systems. Advances in neural information processing systems, 28, 2015.
|
||||
The traditional DLRM architecture, as shown in Fig. 1, follows a modular processing pipeline for CTR prediction, handling raw features from users, candidate ads, and contextual signals. The pipeline involves: (a) expanding categorical features into fixed fields via feature engineering, (b) mapping these fields through hashing to obtain discrete ID vectors for embedding lookup in a Sparse Parameter Server Table (PSTable), and (c) concatenating and normalizing the retrieved embeddings to form a fixed-length flattened vector. This unified representation is then fed into an MLP, typically enhanced with a gating network, to model high-order
|
||||
Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., and Dennison, D. Hidden technical debt in machine learning systems. Advances in neural information processing systems, 28, 2015.
|
||||
|
||||
Sheng, X.-R., Gao, J., Cheng, Y., Yang, S., Han, S., Deng, H., Jiang, Y., Xu, J., and Zheng, B. Joint optimization of ranking and calibration with contextualized hybrid model. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4813–4822, 2023.
|
||||
|
||||
@@ -373,7 +92,9 @@ Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao,
|
||||
|
||||
Zhou, G., Zhu, X., Song, C., Fan, Y., Zhu, H., Ma, X., Yan, Y., Jin, J., Li, H., and Gai, K. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1059–1068, 2018.
|
||||
|
||||
Zhou, G., Mou, N., Fan, Y., Pi, Q., Bian, W., Zhou, C., Zhu, X., and Gai, K. Deep interest evolution network for click-through rate prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pp. 5941–5948, 2019.Zhu, Y., Wu, L., Guo, Q., Hong, L., and Li, J. Collaborative large language model for recommender systems. In Proceedings of the ACM Web Conference 2024, pp. 3162–3172, 2024.### A. Extended Background
|
||||
Zhou, G., Mou, N., Fan, Y., Pi, Q., Bian, W., Zhou, C., Zhu, X., and Gai, K. Deep interest evolution network for click-through rate prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pp. 5941–5948, 2019.
|
||||
Zhu, Y., Wu, L., Guo, Q., Hong, L., and Li, J. Collaborative large language model for recommender systems. In Proceedings of the ACM Web Conference 2024, pp. 3162–3172, 2024.
|
||||
### A. Extended Background
|
||||
|
||||
#### A.1. The Performance-Efficiency Trade-off in Industrial CTR Prediction
|
||||
|
||||
@@ -387,7 +108,8 @@ LLMs have recently emerged as a promising direction for recommendation systems,
|
||||
|
||||
LLM as Recommender. This category explores the direct application of LLM capabilities—such as memory, reasoning, and zero-shot generalization—to core recommendation tasks including retrieval and ranking (Wu et al., 2024; Lin et al., 2025; Xu et al., 2025). Methods in this domain typically adapt recommendation data into natural language prompts, leveraging techniques like Instruction Tuning to align the LLM with recommendation objectives (Zhu et al., 2024; Zhang et al., 2025; Bao et al., 2023; Luo et al., 2025). While these methods demonstrate promise in explainability and conversational recommendation, their performance on traditional metrics (e.g., CTR) often falls short of specialized ID-based models (Liu et al., 2023; Di Palma et al., 2023; Cao et al., 2024). In recommendation scenarios, user behavior is heavily influenced by implicit feedback and specific context rather than the explicit semantic logic found in natural language; consequently, general world-knowledge reasoning does not necessarily translate effectively to modeling complex user-item interaction patterns (Bao et al., 2023; Cao et al., 2024; Zhu et al., 2024). Furthermore, the inference latency remains a significant bottleneck for real-time industrial deployment (Xu et al., 2025).
|
||||
|
||||
LLM for Representation. In this paradigm, LLMs function as sophisticated feature encoders (Lin et al., 2025; Wu et al., 2024). Instead of performing the ranking directly, the intermediate layers or final output embeddings of the LLM are extracted and utilized as semantic features to augment the input of traditional recommendation models (Sun et al., 2024; Jia et al., 2025; Geng et al., 2024; Chen et al., 2024; Ning et al., 2025). This approach aims to enhance the model's semantic understanding without bearing the full cost of LLM inference during the serving phase. LLM-derived representations significantly mitigate the limitations of discrete feature models, particularly regarding the generalization capability forlong-tail items and cold-start users/ads (Hou et al., 2022; 2023). However, this methodology faces notable limitations. There is typically a limited gain on warm items, as the strong collaborative filtering signals derived from abundant historical interactions often outweigh the semantic benefits provided by the LLM (Hou et al., 2023; Lin et al., 2024). Furthermore, employing large-scale models for representation learning introduces a high inference cost, which creates substantial latency and resource bottlenecks during both the offline feature extraction and online serving phases (Lin et al., 2025).
|
||||
LLM for Representation. In this paradigm, LLMs function as sophisticated feature encoders (Lin et al., 2025; Wu et al., 2024). Instead of performing the ranking directly, the intermediate layers or final output embeddings of the LLM are extracted and utilized as semantic features to augment the input of traditional recommendation models (Sun et al., 2024; Jia et al., 2025; Geng et al., 2024; Chen et al., 2024; Ning et al., 2025). This approach aims to enhance the model's semantic understanding without bearing the full cost of LLM inference during the serving phase. LLM-derived representations significantly mitigate the limitations of discrete feature models, particularly regarding the generalization capability for
|
||||
long-tail items and cold-start users/ads (Hou et al., 2022; 2023). However, this methodology faces notable limitations. There is typically a limited gain on warm items, as the strong collaborative filtering signals derived from abundant historical interactions often outweigh the semantic benefits provided by the LLM (Hou et al., 2023; Lin et al., 2024). Furthermore, employing large-scale models for representation learning introduces a high inference cost, which creates substantial latency and resource bottlenecks during both the offline feature extraction and online serving phases (Lin et al., 2025).
|
||||
|
||||
Generative Sequential Modeling. This category represents a structural adaptation rather than a direct semantic application. It borrows the architectural innovations underlying LLMs—specifically the Transformer architecture, Causal Masking, and Long-context modeling capabilities—to reconstruct recommendation systems (Vaswani et al., 2017; Kang & McAuley, 2018; Sun et al., 2019). These models (such as GR models) treat user history as a sequence and the next item prediction as a generative task, similar to next token prediction (Kang & McAuley, 2018; Petrov & Macdonald, 2023; Han et al., 2025). By employing generative sequential modeling techniques and combining them with discrete features that precisely characterize user historical behavior, these models have shown significant potential (Han et al., 2025). A key observation in this domain is the emergence of “scaling laws” within recommendation systems, where model performance metrics improve predictably as the sequence length and model capacity increase (Shin et al., 2023; Zhang et al., 2024b), mirroring the trajectory seen in NLP.
|
||||
|
||||
@@ -411,7 +133,8 @@ This structural mismatch leads to a performance bottleneck: the model conflates
|
||||
|
||||
While GR models have successfully introduced the scaling laws of LLMs into recommendation systems, their direct application to industrial CTR prediction faces distinct structural and optimization challenges.
|
||||
|
||||
Mitigation of Distribution Skew in Sequence Packing. To improve training efficiency with variable-length user sequences, standard GR models often employ sequence packing techniques borrowed from NLP (e.g., concatenating multiple short sequences). However, unlike NLP where samples are generally Independent and Identically Distributed (I.I.D.), packing inrecommendation systems groups multiple interactions from the same user into a single training instance to maintain context. This creates a severe distribution skew, where a mini-batch is dominated by highly correlated samples from a few users. This correlation causes the model—especially the sparse embedding parameters—to overfit specific user identities rather than learning generalizable interaction patterns.
|
||||
Mitigation of Distribution Skew in Sequence Packing. To improve training efficiency with variable-length user sequences, standard GR models often employ sequence packing techniques borrowed from NLP (e.g., concatenating multiple short sequences). However, unlike NLP where samples are generally Independent and Identically Distributed (I.I.D.), packing in
|
||||
recommendation systems groups multiple interactions from the same user into a single training instance to maintain context. This creates a severe distribution skew, where a mini-batch is dominated by highly correlated samples from a few users. This correlation causes the model—especially the sparse embedding parameters—to overfit specific user identities rather than learning generalizable interaction patterns.
|
||||
|
||||
Action heterogeneity. Existing GR models often treat user history as a homogeneous token stream, neglecting the inherent heterogeneity of recommendation data. This reliance on naive serialization discards critical action semantics—distinguishing what was shown from how the user responded—thereby diluting supervision signals and limiting performance in complex industrial scenarios (as discussed in Appendix A.3).
|
||||
|
||||
@@ -441,7 +164,8 @@ where $ T_u $ denotes the length of user $ u $'s behavior history, $ N_u $ de
|
||||
|
||||
Following the discrete feature engineering standard of DLRMs, we apply a structured expansion function $ \Phi $ to transform each event into a fixed multi-field representation. Subsequently, each field value is mapped to a discrete ID via a sparse PSTable $ \Pi $. The event-level representations of the raw behavior sequence and the candidate ad sequence can be obtained as:
|
||||
|
||||
$$ \begin{aligned}\mathbf{x}_{t}^{beh}&=\Pi\big(\Phi\big(S_{t}^{beh}\big)\big),\quad&t&=1,\ldots,T_{u}\\\mathbf{x}_{i}^{ad}&=\Pi\big(\Phi\big(S_{i}^{ad}\big)\big),\quad&i&=1,\ldots,N_{u}\end{aligned} $$ #### C.2. Dense Tokenizer
|
||||
$$ \begin{aligned}\mathbf{x}_{t}^{beh}&=\Pi\big(\Phi\big(S_{t}^{beh}\big)\big),\quad&t&=1,\ldots,T_{u}\\\mathbf{x}_{i}^{ad}&=\Pi\big(\Phi\big(S_{i}^{ad}\big)\big),\quad&i&=1,\ldots,N_{u}\end{aligned} $$
|
||||
#### C.2. Dense Tokenizer
|
||||
|
||||
Unlike the DLRM approach, which concatenates all field embeddings into a fixed-length flattened vector, GRAB preserves the event structure by aggregating field embeddings within each event into a single event token. This yields a time-ordered token sequence that is fed into a Transformer to capture long-range behavioral dependencies and interest drift. Given the structured discrete ID sequences from Section C.1, GRAB converts each event into a dense token for Transformer-based sequential modeling. Specifically, each event is first transformed into a vector through a field-wise embedding lookup followed by a multi-field fusion process, as follows:
|
||||
|
||||
@@ -477,7 +201,8 @@ In sequence packing, we form a packed mini-batch $ \mathcal{B}_{\text{pack}} $
|
||||
|
||||
This issue is most damaging for the sparse embedding table $ \Phi $. Since a packed batch repeatedly contains the same user features (e.g., user_id=123 appears L times along the packed sequence), the update for that single embedding vector is amplified by repeated contributions:
|
||||
|
||||
$$ \Delta\Phi_{u}\propto\sum_{t=1}^{L}\nabla\mathcal{L}_{t}. $$ Such oversized, user-specific updates encourage $ \Phi $ to memorize individual trajectories rather than learn generalizable interaction patterns. Meanwhile, the dense sequence model (e.g., Transformer) suffers from batch-to-batch distribution skew: consecutive packed batches may be dominated by different users (User A $ \rightarrow $ User B), causing abrupt shifts in inputs and gradients, which hinders stable convergence of sequential reasoning parameters.
|
||||
$$ \Delta\Phi_{u}\propto\sum_{t=1}^{L}\nabla\mathcal{L}_{t}. $$
|
||||
Such oversized, user-specific updates encourage $ \Phi $ to memorize individual trajectories rather than learn generalizable interaction patterns. Meanwhile, the dense sequence model (e.g., Transformer) suffers from batch-to-batch distribution skew: consecutive packed batches may be dominated by different users (User A $ \rightarrow $ User B), causing abrupt shifts in inputs and gradients, which hinders stable convergence of sequential reasoning parameters.
|
||||
|
||||
#### D.2. Formalization of STS Stages
|
||||
|
||||
@@ -541,7 +266,8 @@ As illustrated in Fig. 8, the proposed system is implemented within a comprehens
|
||||
|
||||
##### E.1.1. ONLINE SERVING
|
||||
|
||||
The online serving component processes user interactions in real-time. The workflow initiates with a Page View (PV) Request, which sequentially passes through matching and ranking phases to select appropriate advertisements.The core of the ranking mechanism involves a CTR Prediction module that relies on two primary inputs:
|
||||
The online serving component processes user interactions in real-time. The workflow initiates with a Page View (PV) Request, which sequentially passes through matching and ranking phases to select appropriate advertisements.
|
||||
The core of the ranking mechanism involves a CTR Prediction module that relies on two primary inputs:
|
||||
|
||||
• User Representation: A user model processes historical tokens and maintains a KV-cache to efficiently manage state.
|
||||
|
||||
@@ -581,7 +307,8 @@ Hierarchical Parameter Server (PaddleBox). To handle terabyte-scale embedding ta
|
||||
|
||||
• L2 (CPU DRAM): Buffers warm parameters.
|
||||
|
||||
• L3 (SSD): Utilizes NVMe SSDs for massive long-tail feature embeddings. An intelligent prefetching engine asynchronously moves parameters between tiers, masking SSD I/O latency.<div style="text-align: center;"><img src="imgs/img_in_image_box_221_139_977_474.jpg" alt="Image" width="61%" /></div>
|
||||
• L3 (SSD): Utilizes NVMe SSDs for massive long-tail feature embeddings. An intelligent prefetching engine asynchronously moves parameters between tiers, masking SSD I/O latency.
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_221_139_977_474.jpg" alt="Image" width="61%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 8. Overview of an online advertising CTR system with an online-offline closed loop. Online services handle PV requests via matching and ranking, and feed the CTR predictor with user-side historical tokens (maintained by a user model with KV-cache) and candidate ad tokens; user interactions are continuously logged as an impression/action logs. Offline services collect these logs, apply sparse feature engineering, group training samples by user ID, and perform offline training; updated models are released (e.g., hourly) back to online.</div>
|
||||
@@ -599,7 +326,8 @@ Operator Fusion and Mixed Precision. To maximize throughput on GPUs, we employed
|
||||
|
||||
#### E.5. Data Consistency
|
||||
|
||||
A major challenge in GRs is the Freshness Gap (Train-Serve Skew). We addressed this by implementing a streaming data pipeline based on Flink & TableStore. We utilized a Global Strictly Incremental ID mechanism to ensure strict ordering of user actions across distributed nodes. This allows the inference engine to fetch the exact state of the user corresponding to the training checkpoint, reducing data synchronization delay from minutes to seconds and ensuring the model always predicts based on the most consistent context.### F. Discussion
|
||||
A major challenge in GRs is the Freshness Gap (Train-Serve Skew). We addressed this by implementing a streaming data pipeline based on Flink & TableStore. We utilized a Global Strictly Incremental ID mechanism to ensure strict ordering of user actions across distributed nodes. This allows the inference engine to fetch the exact state of the user corresponding to the training checkpoint, reducing data synchronization delay from minutes to seconds and ensuring the model always predicts based on the most consistent context.
|
||||
### F. Discussion
|
||||
|
||||
#### F.1. Limitations and Challenges
|
||||
|
||||
@@ -615,4 +343,295 @@ Towards Multimodal Generative Ranking. Currently, GRAB operates on discretized I
|
||||
|
||||
Unified Generative Representation Across Domains. Finally, the “pre-training & fine-tuning” paradigm common in NLP has yet to be fully realized in industrial recommendation. We envision extending GRAB to learn a Universal User Representation by pre-training on diverse behavior logs across multiple business scenarios (e.g., Home Feed, Search, and Short Video). A unified GRAB model could transfer learned sequential patterns from data-rich domains to cold-start scenarios, effectively solving the “data silo” problem prevalent in large-scale platforms.
|
||||
|
||||
Foundation for Agent-based Recommender Systems. GRAB's ability to model the transition probabilities of user states $ (s_{t} \rightarrow s_{t+1}) $ positions it as a powerful “World Model” or User Simulator for future agent-based recommendation systems. By accurately predicting not just the next click, but the evolution of user interests over time, GRAB can serve as the environment model for Reinforcement Learning (RL) agents. This would allow the system to move beyond myopic CTR optimization toward maximizing Long-Term Value (LTV) or user satisfaction by simulating how current recommendations influence future user trajectories.
|
||||
Foundation for Agent-based Recommender Systems. GRAB's ability to model the transition probabilities of user states $ (s_{t} \rightarrow s_{t+1}) $ positions it as a powerful “World Model” or User Simulator for future agent-based recommendation systems. By accurately predicting not just the next click, but the evolution of user interests over time, GRAB can serve as the environment model for Reinforcement Learning (RL) agents. This would allow the system to move beyond myopic CTR optimization toward maximizing Long-Term Value (LTV) or user satisfaction by simulating how current recommendations influence future user trajectories.
|
||||
feature interactions and generate the final CTR prediction.
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_190_187_498_411.jpg" alt="Image" width="25%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 1. The traditional DLRM architecture: sparse features are hashed to IDs and embedded via PSTable, and then concatenated into a fixed-length flattened vector for CTR prediction.</div>
|
||||
|
||||
|
||||
#### 3.2. Overall Architecture of GRAB
|
||||
|
||||
GRAB, with the overall architecture shown in Fig. 2, is designed to model user behavior history sequences in an end-to-end manner, as applied in scenarios like CTR prediction. GRAB follows a three-stage pipeline: (i) sparse feature layer; (ii) dense tokenizer; and (iii) sequence modeling layer. Given raw behavior logs, GRAB first converts heterogeneous categorical signals into sparse IDs at the event level, then tokenizes each event into a dense representation, and finally applies a sequence model to estimate the click probability of candidate ads. GRAB uses its dense representation calculated from the dense tokenizer to bridge DLRM-style sparse feature engineering and GR-style sequential modeling, enabling end-to-end training and inference along a single, unified computation path from input to output, thereby improving CTR prediction performance through end-to-end sequential modeling of event-level user behaviors.
|
||||
|
||||
Sparse Feature Layer. The sparse feature layer (details in Appendix C.1) processes raw logs into time-ordered event sequences. Each event's categorical fields are converted into sparse IDs using standard DLRM feature engineering (Section 3.1), yielding a structured sequence of events annotated with field-wise IDs.
|
||||
|
||||
Dense Tokenizer. Unlike DLRM, which collapses field embeddings into a fixed-length, order-agnostic vector for pointwise processing, GRAB preserves the temporal event structure. It aggregates per-event field embeddings and projects them into $ \mathbb{R}^{d_{model}} $ to form sequential event tokens (Appendix C.2), resulting in a time-ordered token sequence. This sequence serves as the input to a subsequent Transformer, thereby enabling the modeling of long-range dependencies and interest drift.
|
||||
|
||||
Autoregressive-like Sequence Modeling Layer. Built on sequence packing (Section 3.3.1), heterogeneous tokens (Section 3.3.2), and action-aware relative attention bias (Section 3.3.3), our core contribution is the CamA mechanism (Section 3.3.4). CamA integrates a multi-channel design for parallel processing of diverse behaviors and inherits action-aware contextualization from RAB, providing a unified and efficient framework for modeling complex user interest patterns across scenarios.
|
||||
|
||||
|
||||
|
||||
#### 3.3. Autoregressive-like Sequence Modeling Layer
|
||||
|
||||
Following the dense tokenizer, this layer is designed to capture the temporal dependencies and dynamic evolution of user interests, which takes the sequence of dense event tokens generated by the preceding layer as input (as described in Appendix C.3). Formally, for a user $ u $, the input sequence consists of the behavior history $ \mathbf{E}^{\mathrm{beh}} = \{e_t^{\mathrm{beh}}\}_{t=1}^T $ and the candidate advertisements $ \mathbf{E}^{\mathrm{ad}} = \{e_i^{\mathrm{ad}}\}_{i=1}^N_u $, where $ \mathbf{e}_t^{\mathrm{beh}}, \mathbf{e}_i^{\mathrm{ad}} \in \mathbb{R}^{d_{\mathrm{model}}} $ are the dense embeddings of the $ t $-th behavior event and the $ i $-th candidate ad, respectively, $ T_u $ is the behavior history length, and $ N_u $ is the number of candidate ads.
|
||||
|
||||
##### 3.3.1. SEQUENCE PACKING AND USER-ISOLATED CAUSAL MASK
|
||||
|
||||
In industrial training logs, as shown in the left image of Fig. 3a., a mini-batch is typically formed by sampling $ B_{ins} $ impression instances. Each instance contains a variable-length token sequence composed of (i) a subsequence of the user's historical behavior tokens and (ii) target advertisement tokens to be scored. A straightforward batching strategy pads every instance to a fixed length $ L_{max} $, yielding a dense tensor with dimensions $ B_{ins} \times L_{max} \times d_{model} $,
|
||||
|
||||
which introduces substantial computational waste when most instances are much shorter than $ L_{max} $.
|
||||
|
||||
To eliminate such padding overhead while preserving the temporal semantics, GRAB performs sequence packing by grouping tokens by user. Specifically, tokens from multiple impression instances belonging to the same user u are merged into a single contiguous token segment, while segments of different users are strictly separated. Within each user segment, all tokens are stably sorted by timestamp so that the packed segment forms a single timeline for sequential modeling. After packing, the batch is represented as one long packed tensor $ H = \text{Pack}(\mathbf{E}^{beh}, \mathbf{E}^{ad}) \in \mathbb{R}^{1 \times L \times d_{model}} $, where $ L $ denotes the total packed length across all users in the mini-batch.
|
||||
|
||||
For convenience, we associate each packed position $ p \in \{1, \ldots, L\} $ with (i) a segment $ id \sigma(p) \in U_B $ indicating which user it belongs to, and (ii) a local time index $ \ell(p) \in \{1, \ldots, L_{\sigma(p)}\} $ within that user segment.
|
||||
|
||||
User-isolated causal mask. On the packed tensor $ H $, we construct an additive attention mask $ M^{\text{pack}} \in \mathbb{R}^{L \times L} $ that
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_218_138_976_460.jpg" alt="Image" width="61%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 2. Overview of GRAB's end-to-end CTR prediction pipeline: (1) Tokenizing raw fields via a sparse PSTable and fusing them into event tokens. (2) Packing tokens per user with causal and heterogeneous masks. (3) Processing through N Transformer layers equipped with the Causal Action-aware Multi-channel Attention (CamA) mechanism. (4) Final CTR prediction from the output representations.</div>
|
||||
|
||||
|
||||
enforces two constraints: (1) user isolation (no cross-user attention), and (2) causality within each user's timeline (no future leakage). Formally, for query position p and key position q,
|
||||
|
||||
$$ M_{p,q}^{\mathrm{pack}}=\begin{cases}1,&if\sigma(p)=\sigma(q)and\ell(q)\leq\ell(p),\\0,&otherwise.\end{cases} $$
|
||||
|
||||
This yields a block-diagonal lower-triangular structure (as shown in Fig. 3b), where each block corresponds to one user segment.
|
||||
|
||||
##### 3.3.2. HETEROGENEOUS BEHAVIOR TOKENS AND HETEROGENEOUS VISIBILITY MASK
|
||||
|
||||
After sequence packing, for each user $u$, we obtain a user-isolated, time-ordered packed stream with its causal mask $M_{\text{pack}}$. To further reduce redundancy in the packed history while preserving the information needed for scoring the current candidate, we instantiate two token views at each packed timestamp $t$: the partial token (history) $h_t \in \mathbb{R}^{d_{\text{model}}}$, which retains only time-varying information that is useful for representing history and discards static or highly repetitive fields (e.g., user_id) that would otherwise be duplicated across historical steps and could lead to overfitting; and the full token (candidate) $h'_t \in \mathbb{R}^{d_{\text{model}}}$, which retains the complete information required to score the candidate at time $t$, including the static fields omitted from the partial history view. We then interleave them to form the heterogeneous packed sequence: $H_u = [\mathbf{h}_1, \mathbf{h}_1', \mathbf{h}_2, \mathbf{h}_2', \ldots, \mathbf{h}_{T_u}, \mathbf{h}_{T_u}']$.
|
||||
|
||||
Heterogeneous Visibility Mask. On top of the user-isolated causal constraint encoded by $ M^{pack} $, we apply a mask-rewriting operator $ \mathcal{R}(\cdot) $ to obtain the heterogeneous visibility mask $ M^{het} $. Concretely, $ \mathcal{R}(\cdot) $ rewrites the visibility pattern according to the token types in the following way: (i) partial $ (\mathcal{P}) $ tokens only attend to partial history tokens; and (ii) full $ (\mathcal{F}) $ tokens attend to partial history tokens and themselves, but never attend to other full tokens. Formally, index positions in $ H_u $ by $ n \in \{1, \ldots, 2T_u\} $, we define the time index $ \tau(n) = \lceil n/2 \rceil $ and token type $ \kappa(n) = \mathcal{P} $ if $ n $ is odd, otherwise $ \kappa(n) = \mathcal{F} $. Then the heterogeneous mask (as shown in Fig. 4) is
|
||||
|
||||
|
||||
|
||||
$$ M_{p,q}^{\mathrm{h e t}}=\begin{cases}{1,}&{\kappa(p)=\mathcal{P},\;\kappa(q)=\mathcal{P},\;\tau(q)\leq\tau(p),}\\ {1,}&{\kappa(p)=\mathcal{F},\;\kappa(q)=\mathcal{P},\;\tau(q)\leq\tau(p),}\\ {1,}&{\kappa(p)=\mathcal{F},\;p=q,}\\ {0,}&{\mathrm{o t h e r w i s e}.}\\ \end{cases} $$
|
||||
|
||||
##### 3.3.3. ACTION-AWARE ATTENTION: RELATIVE ENCODING AND EFFICIENT COMPUTATION
|
||||
|
||||
On top of the heterogeneous behavior tokens and the heterogeneous visibility mask $ M^{het} $, we further adopt a action-aware RAB(i.e., relative attention bias) causal attention mechanism. It augments standard multi-head self-attention with three designs: a causal mask to prevent future leakage, a dual sliding-window visibility constraint to support streaming-style training, and a query-aware relative bias that enables the query to directly interact with relative position/time/action signals.
|
||||
|
||||
Action-aware relative attention logits. Given a query $ q_{i} $ and a key $ k_{j} $, the attention logit is computed as
|
||||
|
||||
$$ w_{i,j}=\boldsymbol{q}_{i}^{\top}\cdot\left(k_{j}+P o s_{i,j}+A c t i o n_{i,j}+T i m e_{i,j}\right), $$
|
||||
|
||||
where $ Pos_{i,j} $, $ Action_{i,j} $, and $ Time_{i,j} $ are learnable embeddings derived from relative position, relative action, and relative time, respectively. For continuous or large-range
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_117_147_1083_497.jpg" alt="Image" width="78%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(a) Sequence Packing</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(b) User-isolated Causal Mask</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 3. Sequence packing and user-isolated causal masking in GRAB. (a) Instead of padding each impression instance to a fixed length $ L_{max} $, tokens from multiple impressions are concatenated within each user and different users are kept in disjoint segments, yielding a single packed sequence of length $ N_{token} $ for compute-efficient batching. (b) The user-isolated causal mask exhibits a block-diagonal lower-triangular pattern, so each token can only attend to past tokens within the same user segment, enforcing both user isolation and temporal causality.</div>
|
||||
|
||||
|
||||
signals (e.g., action statistics or play durations), we first discretize them into buckets and then perform embedding lookup.
|
||||
|
||||
Compared with a query-agnostic relative bias (e.g., $ w_{i,j} = q_i^\top k_j + Pos_{i,j} + \cdots $), Eq. 3 makes the relative signals action-aware via the interaction $ q_i^\top Pos_{i,j} $, $ q_i^\top Action_{i,j} $, and $ q_i^\top Time_{i,j} $, allowing the model to adaptively emphasize different contextual relations under different queries (i.e., target ads).
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_246_907_444_1138.jpg" alt="Image" width="16%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 4. Heterogeneous behavior tokens and heterogeneous visibility mask $ M^{het} $ (blue entries). Partial tokens attend only to partial-history tokens up to the current time, while full tokens attend to partial-history tokens up to their time index and to themselves, but never to other full tokens, preventing duplicated static information from propagating along time.</div>
|
||||
|
||||
|
||||
Causal mask with dual sliding windows. We enforce causality and further restrict attention using combined time and length windows. The mask is defined as $ M_{p,q}^{\text{rab}} = 1 $ if $ q \leq p $ and the distance p - q does not exceed the length sliding-window limit $ L_w $; otherwise $ M_{p,q}^{\text{rab}} = 0 $.
|
||||
|
||||
This serves two key industrial purposes: (1) it bounds per-token computation, guaranteeing stable throughput/latency over growing behavior histories; (2) it matches the online training paradigm—events arrive incrementally, and the model updates attention context on the fly without reprocessing the full sequence, boosting training efficiency and serving practicality.
|
||||
|
||||
|
||||
|
||||
Efficient computation. The naive implementation of Eq. 3 would yield an $ O(L^2d_{\text{model}}) $ intermediate tensor, which is prohibitively memory-intensive in practice. We adopt the optimization in (Golovneva et al., 2024) to re-order the computation. We define codebooks $ B^{\text{pos/act/time}} \in \mathbb{R}^{N_s \times d_{\text{model}}} $ and bucketized indices $ p_{i,j}, a_{i,j}, t_{i,j} $. Then Eq. 3 can be equivalently written as:
|
||||
|
||||
$$ w_{i,j}=q_{i}^{\top}k_{j}+(s_{i}^{p o s})[p_{i,j}]+(s_{i}^{a c t})[a_{i,j}]+(s_{i}^{t i m e})[t_{i,j}]. $$
|
||||
|
||||
where $ s_{i}^{\mathrm{pos}} = q_{i}^{\top}B^{\mathrm{pos}} $, $ s_{i}^{\mathrm{act}} = q_{i}^{\top}B^{\mathrm{act}} $, and $ s_{i}^{\mathrm{time}} = q_{i}^{\top}B^{\mathrm{time}} $. In practice, we first compute the projection vectors $ s_{i}^{*} $, then obtain relative terms via fast gather operations. This completely avoids the large $ L \times L \times d_{model} $ tensor, dramatically reducing peak memory and improving computational efficiency.
|
||||
|
||||
##### 3.3.4. MULTI-CHANNEL ATTENTION
|
||||
|
||||
While the action-aware RAB attention (Section 3.3.3) enhances each individual attention logit with relative position/action/time signals, it still treats the packed stream as a single mixed sequence. However, in industrial logs, user behaviors are highly heterogeneous (e.g., spanning different time windows or encompassing different behavior types),
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_image_box_137_140_560_318.jpg" alt="Image" width="34%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 5. Action-aware relative attention bias (RAB) with efficient computation. Left: a causal mask with dual sliding windows, which limits each query to attend only to recent past tokens visible within the sliding-window. Right: the action-aware relative encoding pipeline: relative time, position, and action signals are bucketized (as needed), embedded, summed, and injected to the attention logits.</div>
|
||||
|
||||
|
||||
and different behavioral subsets often exhibit distinct temporal dynamics and predictive value. A straightforward design is to flatten all tokens into a single sequence and apply causal self-attention, yet this couples heterogeneous sources into one interaction graph and incurs a quadratic cost (e.g., $ O((n + m)^2) $ for two sources with lengths $ n $ and $ m $). To improve both modeling effectiveness and efficiency, we further introduce the Causal Action-aware Multi-channel Attention (CamA) mechanism, which integrates a multi-channel design, conceptually analogous to multi-head attention but with channel-specific visibility constraints. We therefore model each channel with an independent causal self-attention stack, and fuse the channel-wise representations via a lightweight gated mixing module. Let $ \mathcal{C} = \{1, \ldots, C\} $ denote the channel set. For each user, channel $ c $ provides a token sequence $ \mathbf{X}^{(c)} \in \mathbb{R}^{T_c \times d} $, and we append the shared target token $ X^{ad} \in \mathbb{R}^d $:
|
||||
|
||||
$$ \mathbf{S}^{(c)}=[\mathbf{X}^{(c)};\mathbf{x}^{\mathrm{t a r}}]\in\mathbb{R}^{(T_{c}+1)\times d},\qquad t^{\star}=T_{c}+1. $$
|
||||
|
||||
Each channel is equipped with its own causal visibility mask $ \mathbf{M}^{(c)} $, and is encoded independently:
|
||||
|
||||
$$ \begin{align*}\mathbf{H}^{(c,\ell+1)}&=\mathrm{Layer}_{\ell}^{(c)}\Big(\tilde{\mathbf{H}}^{(c,\ell)};\mathbf{M}^{(c)}\Big),\\\mathbf{H}^{(c,0)}&=\mathbf{S}^{(c)},\quad c\in\mathcal{C}.\end{align*} $$
|
||||
|
||||
Target-token gated mixing. To enable cross-channel information sharing while keeping computation lightweight, we perform mixing only on the target position $ t^* $ at each layer. The mixed representation $ \tilde{\mathbf{h}}^{(c,\ell)} $ is obtained by first computing channel-wise gating weights $ \beta^{(c,\ell)} $ and then aggregating information from all other channels:
|
||||
|
||||
$$ \tilde{\mathbf{h}}^{(c,\ell)}=\mathbf{h}^{(c,\ell)}+\sum_{i\in\mathcal{C}\backslash\{c\}}\beta^{(i,\ell)}\odot\mathbf{h}^{(i,\ell)}. $$
|
||||
|
||||
This updated representation replaces $ \mathbf{h}^{(c,\ell)} $ at position $ t^{*} $, forming the updated channel representation $ \tilde{\mathbf{H}}^{(c,\ell)} $ used in (6). Finally, the concatenated last-layer target representations from all channels are used for CTR prediction.
|
||||
|
||||
|
||||
|
||||
#### 3.4. Sequence Then Sparse Training
|
||||
|
||||
While sequence packing (Section 3.3.1) significantly enhances computational efficiency, it introduces a critical challenge: distribution skew. Since samples within a packed mini-batch belong to the same user, the high intra-user correlation leads to redundant updates for specific sparse IDs, causing the model to overfit to specific user-ad interactions, rather than learning generalizable patterns. To mitigate this, we propose the Sequence Then Sparse (STS) training paradigm (detailed discussions in Appendix D), a two-stage decoupled optimization strategy that balances long-range sequential modeling with robust sparse feature learning.
|
||||
|
||||
##### 3.4.1. STAGE I: SEQUENCE MODELING (SEQUENCE PHASE)
|
||||
|
||||
The first stage focuses on capturing the evolution of user interests and temporal dependencies. We perform end-to-end autoregressive-like learning on the packed user sequences Z, which include candidate tokens and their historical trajectories. In this phase, we optimize the dense tokenizer and the causal Transformer, while keeping the Sparse Embedding Table $ \Phi $ frozen. By freezing $ \Phi $, we stabilize the token space, forcing the Transformer to focus exclusively on the relational dynamics between events rather than over-memorizing specific ID features.
|
||||
|
||||
##### 3.4.2. STAGE II: SPARSE FEATURE LEARNING (SPARSE PHASE)
|
||||
|
||||
The second stage is designed to refine the discrete representations, particularly for long-tail IDs. In this phase, we revert to a non-sequential format, treating each sample as an independent user-ad exposure to break the distribution skewness. This stage optimizes the sparse embeddings $ \Phi $, which act as a robust corrector for the gradient accumulation amplified by sequence packing. It ensures that the basic feature representations remain accurate and unbiased across the entire traffic distribution.
|
||||
|
||||
### 4. System Deployment
|
||||
|
||||
GRAB has been successfully deployed in a large-scale feed ad ranking system, handling billions of daily requests. Unlike conventional memory-bound DLRMs, GR is markedly compute-bound due to the quadratic complexity of Transformer self-attention. To satisfy stringent latency requirements, we implemented a co-designed hardware-software architecture. Due to space constraints, we provide the comprehensive system overview (Fig. 8) and detailed deployment optimizations in Appendix E.
|
||||
### 5. Experiment
|
||||
|
||||
#### 5.1. Overall Performance Comparison
|
||||
|
||||
We first compared the performance of GRAB against state-of-the-art recommendation models on the Baidu real-world industrial dataset. The training data, derived from the Baidu real recommendation advertising scene, contains billions of users, exposure logs, and click logs. The test set includes millions of users, billions of exposure logs, and millions of click logs. The baselines encompass both DL-RMs and GR models, including: DIN (Zhou et al., 2018), which models short-term user behavior with target attention; SIM(Soft) (Pi et al., 2020), a sequential model that uses soft-search to encode user interests; TWIN (Si et al., 2024), which extends multi-head target attention from ESU to GSU; HSTU (Zhai et al., 2024), an efficient model for long-sequence behavior modeling; and LONGER (Chai et al., 2025), a Transformer-based architecture designed for ultra-long behavior sequences. Experimental results are presented in Table 1: GRAB outperforms all other baselines, achieving a 0.19% relative improvement over the most competitive model. Meanwhile, Fig. 6a illustrates the performance of different models across varying lengths of user behavior sequences. GRAB surpasses other recommendation models at all sequence lengths, with its performance gains becoming more pronounced as the sequence length increases.
|
||||
|
||||
<div style="text-align: center;">Table 1. Overall performance in industrial settings</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>AUC</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>DIN</td><td style='text-align: center; word-wrap: break-word;'>0.83309</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>SIM Soft</td><td style='text-align: center; word-wrap: break-word;'>0.83520</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>TWIN</td><td style='text-align: center; word-wrap: break-word;'>0.83556</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>HSTU</td><td style='text-align: center; word-wrap: break-word;'>0.83590</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>LONGER</td><td style='text-align: center; word-wrap: break-word;'>0.83615</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB-small</td><td style='text-align: center; word-wrap: break-word;'>0.83661</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB-standard</td><td style='text-align: center; word-wrap: break-word;'>0.83772</td></tr></table>
|
||||
|
||||
#### 5.2. Scaling Analysis
|
||||
|
||||
We evaluate model performance across different capacity scales by independently scaling the number of Transformer blocks( $ n_{layer} $), the number of attention heads( $ n_{head} $), and the feature dimension of the model( $ d_{model} $) in Table 2, Fig. 6b presents the test-set performance of the GRAB model under varying configurations (i.e., $ n_{layer} $, $ n_{head} $ and $ d_{model} $). These results demonstrate that increasing model capacity effectively improves model performance. We also found that as the model capacity increases, the performance improvement on longer user behavior sequences becomes more significant. Moreover, no significant saturation trend is observed within the current range of configurations, which also confirms the strong scalability of the GRAB model.
|
||||
|
||||
<div style="text-align: center;">Table 2. Comparison of models with different settings</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>Params</td><td style='text-align: center; word-wrap: break-word;'>Setting</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{2l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.51M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=2 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.67M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{6l-2h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.83M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=6 $, $ n_{head}=2 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{2l-4h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.48M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=2 $, $ n_{head}=4 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-64d} $</td><td style='text-align: center; word-wrap: break-word;'>6.63M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=64 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-128d} $</td><td style='text-align: center; word-wrap: break-word;'>7.05M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=128 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-256d} $</td><td style='text-align: center; word-wrap: break-word;'>8.13M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=256 $</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB $ _{4l-4h-512d} $</td><td style='text-align: center; word-wrap: break-word;'>11.27M</td><td style='text-align: center; word-wrap: break-word;'>$ n_{layer}=4 $, $ n_{head}=4 $, $ d_{model}=512 $</td></tr></table>
|
||||
|
||||
#### 5.3. Ablation Study
|
||||
|
||||
Heterogeneous Tokens. We conduct ablation studies on heterogeneous representations with three configurations: GRAB with heterogeneous, only partial, or only full tokens (Table 3). Results show that heterogeneous representations achieve the best performance. Using only partial tokens leads to significant degradation, confirming that full feature representations are more beneficial for target scoring. Notably, using only full tokens also degrades performance, suggesting that artificially designed statistical features can introduce confusion and impair sequence modeling.
|
||||
|
||||
<div style="text-align: center;">Table 3. Ablation studies of GRAB</div>
|
||||
|
||||
|
||||
|
||||
<table border=1 style='margin: auto; word-wrap: break-word;'><tr><td style='text-align: center; word-wrap: break-word;'>Model</td><td style='text-align: center; word-wrap: break-word;'>AUC</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB</td><td style='text-align: center; word-wrap: break-word;'>0.83772</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/ Partial Token</td><td style='text-align: center; word-wrap: break-word;'>0.83492</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/ Full Token</td><td style='text-align: center; word-wrap: break-word;'>0.83749</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative pos</td><td style='text-align: center; word-wrap: break-word;'>0.83768</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative time</td><td style='text-align: center; word-wrap: break-word;'>0.83743</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o relative action</td><td style='text-align: center; word-wrap: break-word;'>0.83724</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o Multi-channel</td><td style='text-align: center; word-wrap: break-word;'>0.83743</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB w/o Target-token mix</td><td style='text-align: center; word-wrap: break-word;'>0.83768</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB_sparse</td><td style='text-align: center; word-wrap: break-word;'>0.83614</td></tr><tr><td style='text-align: center; word-wrap: break-word;'>GRAB_sparse w/o STS</td><td style='text-align: center; word-wrap: break-word;'>0.83549</td></tr></table>
|
||||
|
||||
Action-aware Attention. We ablate three components of GRAB's Action-aware Attention: relative position, time, and action. The results (Table 3) show that removing any of these components degrades performance. The decline is more pronounced for time and action than for position, indicating that historical sequences are more sensitive to behavioral and temporal signals. We also analyze the attention weight distribution across buckets defined by relative position/time differences (smaller values denote more recent tokens). As shown in Figure 7, weights decrease as bucket values increase, confirming that more recent behaviors better reflect user interest and receive higher weights. For relative action, we compare positive (click) and negative (non-click) labels. The weight distribution is highly skewed: positive labels account for 88% of the total weight, versus only 12%
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_chart_box_110_146_498_401.jpg" alt="Image" width="31%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(a) Overall Performance</div>
|
||||
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_chart_box_694_136_1079_398.jpg" alt="Image" width="31%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">(b) Scaling Performance</div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 6. DLRMs vs. GRs across different user behavior sequence lengths (a), with a +0.1% improvement in AUC, indicating a significant enhancement. GRABs comparison in different parameter scale(b)</div>
|
||||
|
||||
|
||||
for negative labels. This suggests that incorporating more positive feedback could further improve sequence modeling.
|
||||
|
||||
<div style="text-align: center;"><img src="imgs/grab/img_in_chart_box_172_627_504_881.jpg" alt="Image" width="27%" /></div>
|
||||
|
||||
|
||||
<div style="text-align: center;">Figure 7. The weight distribution of action-aware attention in relative position and relative time.</div>
|
||||
|
||||
|
||||
Multi-channel Attention. To verify the effectiveness of multi-channel attention in sequence modeling, we conduct the following settings: 1) the GRAB model without multi-channel attention, that is, using a single channel for sequence modeling, 2) remain the multi-channel attention and only remove the target token mix component. As shown in Table 3, both configurations have varying degrees of performance degradation, indicating that each component is indispensable. In terms of performance, multi-channel attention is crucial, and adding the target token mix component can further improve performance.
|
||||
|
||||
STS Training. We evaluate the STS paradigm by comparing GRAB's second-stage training with and without sequence modeling for sparse feature learning. With STS, sparse embeddings are updated through sequence modeling on packed user behavior sequences; without STS, the same batch data is treated as independent exposures. Results (as shown in Table 3) show that STS brings significant accuracy gains in sparse feature learning, confirming the efficacy of the two-stage training. This demonstrates that STS alleviates the distribution skew and overfitting caused by direct sequence-packed training.
|
||||
|
||||
|
||||
|
||||
#### 5.4. Online A/B Test
|
||||
|
||||
To assess the online performance of GRAB, we deployed it in Baidu home feed scenario of Baidu and compared its performance with the current online DLRM model. The experiment used 10% of the main traffic and remained online for about a month. Online evaluation shows that GRAB delivered 3.49% improvement in CTR and 3.05% improvement in CPM, which indicates that GRAB achieves more accurate advertising estimation and brings considerable revenue increments. Notably, GRAB has already been fully deployed on Baidu, and the online inference costs on par with the previous online DLRM model.
|
||||
|
||||
### 6. Conclusion
|
||||
|
||||
We propose GRAB, an end-to-end generative ranking framework that integrates a novel CamA mechanism to effectively capture temporal dynamics and specific action signals within user behavior sequences. On Baidu billion-scale industrial dataset, GRAB establishes a new state-of-the-art, outperforming DLRM and other GR baselines. Ablation studies validate the necessity of its key components, and our proposed STS training paradigm effectively mitigates distribution shift. Scaling analysis indicates continued gains from larger models and longer sequences. Finally, full online A/B testing in Baidu home feed ads shows that GRAB boosts CTR by 3.49% and CPM by 3.05%, leading to full production deployment. Further discussion of this work can be found in the Appendix F.
|
||||
## References
|
||||
|
||||
Agarwal, S., Yan, C., Zhang, Z., and Venkataraman, S. Bagpipe: Accelerating deep recommendation model training. In Proceedings of the 29th Symposium on Operating Systems Principles, pp. 348–363, 2023.
|
||||
|
||||
Bai, J., Geng, X., Deng, J., Xia, Z., Jiang, H., Yan, G., and Liang, J. A comprehensive survey on advertising click-through rate prediction algorithm. The Knowledge Engineering Review, 40:e3, 2025.
|
||||
|
||||
Bao, K., Zhang, J., Zhang, Y., Wang, W., Feng, F., and He, X. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In Proceedings of the 17th ACM conference on recommender systems, pp. 1007–1014, 2023.
|
||||
|
||||
Cao, Y., Mehta, N., Yi, X., Keshavan, R. H., Heldt, L., Hong, L., Chi, E., and Sathiamoorthy, M. Aligning large language models with recommendation knowledge. In Findings of the Association for Computational Linguistics: NAACL 2024, pp. 1051–1066, 2024.
|
||||
|
||||
Baylor, D., Breck, E., Cheng, H.-T., Fiedel, N., Foo, C. Y., Haque, Z., Haykal, S., Ispir, M., Jain, V., Koc, L., et al. Tfx: A tensorflow-based production-scale machine learning platform. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1387–1395, 2017.
|
||||
|
||||
Chai, Z., Ren, Q., Xiao, X., Yang, H., Han, B., Zhang, S., Chen, D., Lu, H., Zhao, W., Yu, L., et al. Longer: Scaling up long sequence modeling in industrial recommenders. In Proceedings of the Nineteenth ACM Conference on Recommender Systems, pp. 247–256, 2025.
|
||||
|
||||
Chen, J., Chi, L., Peng, B., and Yuan, Z. Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740, 2024.
|
||||
|
||||
Cheng, H.-T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., et al. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems, pp. 7–10, 2016.
|
||||
|
||||
Covington, P., Adams, J., and Sargin, E. Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM conference on recommender systems, pp. 191–198, 2016.
|
||||
|
||||
Di Palma, D., Biancofiore, G. M., Anelli, V. W., Narducci, F., Di Noia, T., and Di Sciascio, E. Evaluating chatgpt as a recommender system: A rigorous approach. arXiv preprint arXiv:2309.03613, 2023.
|
||||
|
||||
Doan, T. T., Nguyen, L. M., Pham, N. H., and Romberg, J. Finite-time analysis of stochastic gradient descent under markov randomness. arXiv preprint arXiv:2003.10973, 2020.
|
||||
|
||||
Geng, B., Huan, Z., Zhang, X., He, Y., Zhang, L., Yuan, F., Zhou, J., and Mo, L. Breaking the length barrier: Llm-enhanced ctr prediction in long textual user behaviors. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2311–2315, 2024.
|
||||
|
||||
Golovneva, O., Wang, T., Weston, J., and Sukhbaatar, S. Contextual position encoding: Learning to count what's important. arXiv preprint arXiv:2405.18719, 2024.
|
||||
|
||||
Guo, H., Tang, R., Ye, Y., Li, Z., and He, X. Deepfm: a factorization-machine based neural network for ctr prediction. arXiv preprint arXiv:1703.04247, 2017.
|
||||
|
||||
Han, R., Yin, B., Chen, S., Jiang, H., Jiang, F., Li, X., Ma, C., Huang, M., Li, X., Jing, C., et al. Mtgr: Industrial-scale generative recommendation framework in meituan. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pp. 5731–5738, 2025.
|
||||
|
||||
He, X., Pan, J., Jin, O., Xu, T., Liu, B., Xu, T., Shi, Y., Atallah, A., Herbrich, R., Bowers, S., et al. Practical lessons from predicting clicks on ads at facebook. In Proceedings of the eighth international workshop on data mining for online advertising, pp. 1–9, 2014.
|
||||
|
||||
He, Z., Xie, Z., Jha, R., Steck, H., Liang, D., Feng, Y., Majumder, B. P., Kallus, N., and McAuley, J. Large language models as zero-shot conversational recommenders. In Proceedings of the 32nd ACM international conference on information and knowledge management, pp. 720–730, 2023.
|
||||
|
||||
Hou, Y., Mu, S., Zhao, W. X., Li, Y., Ding, B., and Wen, J.-R. Towards universal sequence representation learning for recommender systems. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp. 585–593, 2022.
|
||||
|
||||
Hou, Y., He, Z., McAuley, J., and Zhao, W. X. Learning vector-quantized item representation for transferable sequential recommenders. In Proceedings of the ACM Web Conference 2023, pp. 1162–1171, 2023.
|
||||
|
||||
Jia, J., Wang, Y., Li, Y., Chen, H., Bai, X., Liu, Z., Liang, J., Chen, Q., Li, H., Jiang, P., et al. Learn: Knowledge adaptation from large language model to recommendation for practical industrial application. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pp. 11861–11869, 2025.
|
||||
Kang, W.-C. and McAuley, J. Self-attentive sequential recommendation. In 2018 IEEE international conference on data mining (ICDM), pp. 197–206. IEEE, 2018.
|
||||
|
||||
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020.
|
||||
|
||||
Krell, M. M., Kosec, M., Perez, S. P., and Fitzgibbon, A. Efficient sequence packing without cross-contamination: Accelerating large language models without impacting performance. arXiv preprint arXiv:2107.02027, 2021.
|
||||
|
||||
Li, L., Zhang, Y., Liu, D., and Chen, L. Large language models for generative recommendation: A survey and visionary discussions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 10146–10159, 2024a.
|
||||
|
||||
Li, R., Deng, W., Cheng, Y., Yuan, Z., Zhang, J., and Yuan, F. Exploring the upper limits of text-based collaborative filtering using large language models: Discoveries and insights. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pp. 1643–1653, 2025.
|
||||
|
||||
Li, S., Guo, H., Tang, X., Tang, R., Hou, L., Li, R., and Zhang, R. Embedding compression in recommender systems: A survey. ACM Computing Surveys, 56(5):1–21, 2024b.
|
||||
|
||||
Lin, J., Dai, X., Xi, Y., Liu, W., Chen, B., Zhang, H., Liu, Y., Wu, C., Li, X., Zhu, C., et al. How can recommender systems benefit from large language models: A survey. ACM Transactions on Information Systems, 43(2):1–47, 2025.
|
||||
|
||||
Lin, Z., Ding, H., Hoang, N. T., Kveton, B., Deoras, A., and Wang, H. Pre-trained recommender systems: A causal debiasing perspective. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 424–433, 2024.
|
||||
|
||||
Liu, J., Liu, C., Zhou, P., Lv, R., Zhou, K., and Zhang, Y. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149, 2023.
|
||||
|
||||
Luo, S., He, B., Zhao, H., Shao, W., Qi, Y., Huang, Y., Zhou, A., Yao, Y., Li, Z., Xiao, Y., et al. Recranker: Instruction tuning large language model as ranker for top-k recommendation. ACM Transactions on Information Systems, 43(5):1–31, 2025.
|
||||
|
||||
Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., and Chi, E. H. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th
|
||||
|
||||
ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1930–1939, 2018a.
|
||||
|
||||
Ma, X., Zhao, L., Huang, G., Wang, Z., Hu, Z., Zhu, X., and Gai, K. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1137–1140, 2018b.
|
||||
|
||||
Mudigere, D., Hao, Y., Huang, J., Jia, Z., Tulloch, A., Sridharan, S., Liu, X., Ozdal, M., Nie, J., Park, J., et al. Software-hardware co-design for fast and scalable training of deep learning recommendation models. In Proceedings of the 49th Annual International Symposium on Computer Architecture, pp. 993–1011, 2022.
|
||||
|
||||
Naumov, M., Mudigere, D., Shi, H.-J. M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C.-J., Azzolini, A. G., et al. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091, 2019.
|
||||
|
||||
Ning, L., Liu, L., Wu, J., Wu, N., Berlowitz, D., Prakash, S., Green, B., O'Banion, S., and Xie, J. User-llm: Efficient llm contextualization with user embeddings. In Companion Proceedings of the ACM on Web Conference 2025, pp. 1219–1223, 2025.
|
||||
|
||||
Petrov, A. V. and Macdonald, C. Generative sequential recommendation with gptrec. arXiv preprint arXiv:2306.11114, 2023.
|
||||
|
||||
Pi, Q., Bian, W., Zhou, G., Zhu, X., and Gai, K. Practice on long sequential user behavior modeling for click-through rate prediction. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 2671–2679, 2019.
|
||||
|
||||
Pi, Q., Zhou, G., Zhang, Y., Wang, Z., Ren, L., Fan, Y., Zhu, X., and Gai, K. Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2685–2692, 2020.
|
||||
|
||||
Polyzotis, N., Zinkevich, M., Roy, S., Breck, E., and Whang, S. Data validation for machine learning. Proceedings of machine learning and systems, 1:334–347, 2019.
|
||||
|
||||
Rajput, S., Mehta, N., Singh, A., Hulikal Keshavan, R., Vu, T., Heldt, L., Hong, L., Tay, Y., Tran, V., Samost, J., et al. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, 36: 10299–10315, 2023.
|
||||
|
||||
+455
-429
File diff suppressed because one or more lines are too long
Binary file not shown.
|
After Width: | Height: | Size: 32 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 26 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 35 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 81 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 29 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 87 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 74 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 37 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 13 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 10 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 27 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 28 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 31 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 18 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 19 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 23 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 59 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 58 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 28 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 30 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 10 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 85 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 49 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 115 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 55 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 79 KiB |
Reference in New Issue
Block a user