mlsanityData to 7 Oct 2026

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

arXiv 2108.04468 ↗First posted 10 Aug 2021cs.IR cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

29 of 39 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2020Reformer: The Efficient Transformercited by 1,658
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  6. 2018Self-Attentive Sequential Recommendationcited by 1,169
  7. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  8. 2016Wide & Deep Learning for Recommender Systemscited by 745
  9. 2015Session-based Recommendations with Recurrent Neural Networkscited by 685
  10. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  11. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  12. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 473
17 more
  1. 2017Deep & Cross Network for Ad Click Predictionscited by 392
  2. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 336
  3. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 277
  4. 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 176
  5. 2016Product-based Neural Networks for User Response Predictioncited by 145
  6. 2017Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networkscited by 126
  7. 2018A Simple Convolutional Generative Network for Next Item Recommendationcited by 120
  8. 2019Practice on Long Sequential User Behavior Modeling for Click-Through Rate Predictioncited by 118
  9. 2019Multi-Interest Network with Dynamic Routing for Recommendation at Tmallcited by 113
  10. 2015Practical and Optimal LSH for Angular Distancecited by 105
  11. 2016Deep Learning over Multi-field Categorical Data: A Case Study on User Response Predictioncited by 67
  12. 2019Deep Session Interest Network for Click-Through Rate Predictioncited by 64
  13. 2018Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertisingcited by 59
  14. 2020User Behavior Retrieval for Click-Through Rate Predictioncited by 44
  15. 2019Lifelong Sequential Modeling with Personalized Memorization for User Response Predictioncited by 41
  16. 2019Joint Optimization of Tree-based Index and Deep Model for Recommender Systemscited by 37
  17. 2020Deep Interest with Hierarchical Attention Network for Click-Through Rate Predictioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 6; 2025: 15; 2026: 10.

45 papers.

Sort:

By area:

  1. 2023Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Modelscited by 40
  2. 2024TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishoucited by 30
  3. 2023A Survey on User Behavior Modeling in Recommender Systemscited by 26
  4. 2022Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Predictioncited by 24
  5. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 22
  6. 2024Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendationcited by 16
  7. 2023Temporal Interest Network for User Response Predictioncited by 9
  8. 2023PIER: Permutation-Level Interest-Based End-to-End Re-ranking Framework in E-commercecited by 8
  9. 2024Long-Sequence Recommendation Models Need Decoupled Embeddingscited by 7
  10. 2025MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modelingcited by 6
  11. 2022BASM: A Bottom-up Adaptive Spatiotemporal Model for Online Food Ordering Servicecited by 5
  12. 2025NLGR: Utilizing Neighbor Lists for Generative Rerank in Personalized Recommendation Systemscited by 5
33 more
  1. 2025Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Predictioncited by 4
  2. 2026HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendationcited by 4
  3. 2023ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraintcited by 3
  4. 2023ConvFormer: Revisiting Transformer for Sequential User Modelingcited by 3
  5. 2023TBIN: Modeling Long Textual Behavior Data for CTR Predictioncited by 3
  6. 2023Fragment and Integrate Network (FIN): A Novel Spatial-Temporal Modeling Based on Long Sequential Behavior for Online Food Ordering Click-Through Rate Predictioncited by 3
  7. 2025Action is All You Need: Dual-Flow Generative Ranking Network for Recommendationcited by 3
  8. 2025GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Modelscited by 3
  9. 2025LLM-Aligned Geographic Item Tokenization for Local-Life Recommendationcited by 3
  10. 2022AutoAttention: Automatic Field Pair Selection for Attention in User Behavior Modelingcited by 2
  11. 2024A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Searchcited by 2
  12. 2025Pre-train and Fine-tune: Recommenders as Large Modelscited by 2
  13. 2025SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendationcited by 2
  14. 2025Equip Pre-ranking with Target Attention by Residual Quantizationcited by 2
  15. 2026RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inferencecited by 2
  16. 2026Beyond Interleaving: Causal Attention Reformulations for Generative Recommender Systemscited by 2
  17. 2024Retrieval-Oriented Knowledge for Click-Through Rate Predictioncited by 1
  18. 2025Generative Click-through Rate Prediction with Applications to Search Advertisingcited by 1
  19. 2025MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendationcited by 1
  20. 2025Target-Aware Early Stage Rankingcited by 1
  21. 2026UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendationcited by 1
  22. 2022Hierarchical Multi-Interest Co-Network For Coarse-Grained Rankingcited by 0
  23. 2023A Deep Behavior Path Matching Network for Click-Through Rate Predictioncited by 0
  24. 2023Context-aware Session-based Recommendation with Graph Neural Networkscited by 0
  25. 2025Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 0
  26. 2025GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillationcited by 0
  27. 2025Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Predictioncited by 0
  28. 2026MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendationcited by 0
  29. 2026Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scalecited by 0
  30. 2026UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequencecited by 0
  31. 2026Generative Long-term User Interest Modeling for Click-Through Rate Predictioncited by 0
  32. 2026Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendationcited by 0
  33. 2026SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Cachingcited by 0