Pith. sign in

REVIEW 17 cited by

End-to-End User Behavior Retrieval in Click-Through RatePrediction Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.04468 v1 pith:OU2NRQLA submitted 2021-08-10 cs.IR cs.AI

Qiwei Chen , Changhua Pei , Shanshan Lv , Chao Li , Junfeng Ge , Wenwu Ou This is my paper · ORCID
classification cs.IRcs.AI
keywords usersequencebehaviorlong-termmodelstageend-to-endgreatly
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair. Recently, researchers have found that the performance of CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term user behavior sequence. The report on an e-commerce website shows that 23\% of users have more than 1000 clicks during the past 5 months. Though there are numerous works focus on modeling sequential user behaviors, few works can handle long-term user behavior sequence due to the strict inference time constraint in real world system. Two-stage methods are proposed to push the limit for better performance. At the first stage, an auxiliary task is designed to retrieve the top-$k$ similar items from long-term user behavior sequence. At the second stage, the classical attention mechanism is conducted between the candidate item and $k$ items selected in the first stage. However, information gap happens between retrieval stage and the main CTR task. This goal divergence can greatly diminishing the performance gain of long-term user sequence. In this paper, inspired by Reformer, we propose a locality-sensitive hashing (LSH) method called ETA (End-to-end Target Attention) which can greatly reduce the training and inference cost and make the end-to-end training with long-term user behavior sequence possible. Both offline and online experiments confirm the effectiveness of our model. We deploy ETA into a large-scale real world E-commerce system and achieve extra 3.1\% improvements on GMV (Gross Merchandise Value) compared to a two-stage long user sequence CTR model.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models

    cs.IR 2026-04 unverdicted novelty 7.0 of 10

    SIF replaces item-ID history tokens with lossily compressed full-sample tokens and reports consistent CTR/CVR gains in offline and live recommender tests.

  2. SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

    cs.IR 2026-08 conditional novelty 6.0 of 10

    SITA learns semantic interest tokens per user and selects them with per-item semantic codes, giving target-aware long-sequence modeling at O(N) inference cost.

  3. MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders

    cs.IR 2026-02 conditional novelty 6.0 of 10

    MixFormer unifies dense feature interaction and user-sequence modeling in a single Transformer-style backbone with a user-item decoupling speedup, reporting accuracy and efficiency gains over stacked and parallel reco...

  4. MTGR: Industrial-Scale Generative Recommendation Framework in Meituan

    cs.IR 2025-05 conditional novelty 6.0 of 10

    MTGR augments an HSTU-style generative ranking model with DLRM cross features and user-level aggregation, and reports a successful industrial deployment at Meituan with offline and online gains.

  5. Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation

    cs.IR 2025-05 conditional novelty 6.0 of 10

    DFGR, a dual-flow generative ranking network, halves training cost and quarters inference cost versus HSTU-based generative ranking while reporting better offline AUC/G-AUC on public and industrial datasets.

  6. SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendation

    cs.IR 2025-02 conditional novelty 6.0 of 10

    SessionRec redefines generative sequential recommendation as next-session prediction and reports large Recall@500 gains over next-item baselines on two industrial datasets.

  7. NLGR: Utilizing Neighbor Lists for Generative Rerank in Personalized Recommendation Systems

    cs.IR 2025-02 conditional novelty 6.0 of 10

    Training a generative re-ranker on relative scores of neighboring item lists, plus a sampling-based non-autoregressive decoder, improves CTR and GMV in Meituan's food delivery recommender.

  8. Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation

    cs.IR 2026-07 conditional novelty 5.5 of 10

    Disentangling LLM hidden states into attribute-aligned geo and semantic slots before dual-stream residual quantization cuts SID collisions and improves local-life recommendation AUC.

  9. MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

    cs.IR 2025-09 conditional novelty 5.0 of 10

    MARS aligns text and image features of items, then augments sparse user sequences with retrieved sequences from similar heavy users, improving CTR prediction offline and online.

  10. Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction

    cs.IR 2025-08 conditional novelty 5.0 of 10

    Diff-MSIN improves multi-modal CTR prediction AUC by roughly 1.5-2% over prior multi-modal baselines by disentangling common, specific, and synergistic modality features.

  11. MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation

    cs.IR 2025-08 conditional novelty 5.0 of 10

    MISS builds a k-means index tree on interaction-supervised multi-modal embeddings and adds two behavior search units (Co-GSU, MM-GSU) plus ESU/MMoE, reporting ~30-47% relative recall gains over TDM+MMoE on Kuaishou da...

  12. User Long-Term Multi-Interest Retrieval Model for Recommendation

    cs.IR 2025-07 conditional novelty 5.0 of 10

    ULIM clusters a user's long behavior history into category subsequences and uses a pointer-generator network to predict categories, then retrieves items within those categories in parallel.

  13. USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations

    cs.IR 2025-07 reject novelty 5.0 of 10

    USD combines portal-intent-based sampling with dual intent-weighted debiasing to improve homepage CTR prediction, reporting 35.4% and 14.5% UCTR gains in online tests.

  14. GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation

    cs.AI 2025-07 conditional novelty 5.0 of 10

    GIST improves cross-domain CTR prediction by distilling content and behavior signals into joint item embeddings used for lifelong-sequence search and similarity-based features.

  15. Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation

    cs.IR 2026-02 conditional novelty 4.0 of 10

    GLASS extends generative retrieval with a tiered long-term interest vector and a first-SID-keyed search of long histories, reporting consistent gains over Tiger and DualGR on two public datasets.

  16. FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation

    cs.IR 2025-02 conditional novelty 4.0 of 10

    FARM combines discrete Fourier frequency splitting with contrastive preference alignment to improve cross-domain live-streaming recommendation at Kuaishou.

  17. GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models

    cs.IR 2025-07 unverdicted novelty 3.0 of 10

    A survey of LLM-based generative recommendation systems, covering application settings, training pipelines, industrial deployment challenges, and future directions.

Pith tools