TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou

• URL: http://arxiv.org/abs/2407.16357v2
• Date: Fri, 16 Aug 2024 05:16:31 GMT
• Title: TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
• Authors: Zihua Si, Lin Guan, ZhongXiang Sun, Xiaoxue Zang, Jing Lu, Yiqun Hui, Xingchao Cao, Zeyu Yang, Yichen Zheng, Dewei Leng, Kai Zheng, Chenbin Zhang, Yanan Niu, Yang Song, Kun Gai,
• Abstract summary: We introduce TWIN-V2, an enhancement of SIM, where a divide-and-conquer approach is applied to compress life-cycle behaviors and uncover more accurate and diverse user interests. Under an efficient deployment framework, TWIN-V2 has been successfully deployed to the primary traffic that serves hundreds of millions of daily active users at Kuaishou.
• Score: 28.809014888174932
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The significance of modeling long-term user interests for CTR prediction tasks in large-scale recommendation systems is progressively gaining attention among researchers and practitioners. Existing work, such as SIM and TWIN, typically employs a two-stage approach to model long-term user behavior sequences for efficiency concerns. The first stage rapidly retrieves a subset of sequences related to the target item from a long sequence using a search-based mechanism namely the General Search Unit (GSU), while the second stage calculates the interest scores using the Exact Search Unit (ESU) on the retrieved results. Given the extensive length of user behavior sequences spanning the entire life cycle, potentially reaching up to 10^6 in scale, there is currently no effective solution for fully modeling such expansive user interests. To overcome this issue, we introduced TWIN-V2, an enhancement of TWIN, where a divide-and-conquer approach is applied to compress life-cycle behaviors and uncover more accurate and diverse user interests. Specifically, a hierarchical clustering method groups items with similar characteristics in life-cycle behaviors into a single cluster during the offline phase. By limiting the size of clusters, we can compress behavior sequences well beyond the magnitude of 10^5 to a length manageable for online inference in GSU retrieval. Cluster-aware target attention extracts comprehensive and multi-faceted long-term interests of users, thereby making the final recommendation results more accurate and diverse. Extensive offline experiments on a multi-billion-scale industrial dataset and online A/B tests have demonstrated the effectiveness of TWIN-V2. Under an efficient deployment framework, TWIN-V2 has been successfully deployed to the primary traffic that serves hundreds of millions of daily active users at Kuaishou.

Related papers

• Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction [68.90783662117936]
  Click-through Rate (CTR) prediction is crucial for online personalization platforms. Recent advancements have shown that modeling rich user behaviors can significantly improve the performance of CTR prediction. We propose Multi-granularity Interest Retrieval and Refinement Network (MIRRN)
  arXiv  Detail & Related papers  (2024-11-22T15:29:05Z)
• Long-Sequence Recommendation Models Need Decoupled Embeddings [49.410906935283585]
  We identify and characterize a neglected deficiency in existing long-sequence recommendation models. A single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes. We propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are learned separately to fully decouple attention and representation.
  arXiv  Detail & Related papers  (2024-10-03T15:45:15Z)
• SEMINAR: Search Enhanced Multi-modal Interest Network and Approximate Retrieval for Lifelong Sequential Recommendation [16.370075234443245]
  We propose a unified lifelong multi-modal sequence model called SEMINAR-Search Enhanced Multi-Modal Interest Network and Approximate Retrieval. Specifically, a network called Pretraining Search Unit learns the lifelong sequences of multi-modal query-item pairs in a pretraining-finetuning manner. To accelerate the online retrieval speed of multi-modal embedding, we propose a multi-modal codebook-based product quantization strategy.
  arXiv  Detail & Related papers  (2024-07-15T13:33:30Z)
• Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences [10.233015715433602]
  We propose a Sparse Attentive Memory network for long sequential user behavior modeling. SAM supports efficient training and real-time inference for user behavior sequences with lengths on the scale of thousands. SAM is successfully deployed on one of the largest international E-commerce platforms.
  arXiv  Detail & Related papers  (2022-08-08T10:11:46Z)
• Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction [97.99938802797377]
  Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in recommender systems. Recent deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. We propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper.
  arXiv  Detail & Related papers  (2022-06-28T03:28:15Z)
• Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction [15.97120392599086]
  We propose textbfM (textbfSampling-based textbfDeep textbfModeling), a simple yet effective sampling-based end-to-end approach for modeling long-term user behaviors. We show theoretically and experimentally that the proposed method performs on par with standard attention-based models on modeling long-term user behaviors.
  arXiv  Detail & Related papers  (2022-05-20T15:20:52Z)
• Sequential Search with Off-Policy Reinforcement Learning [48.88165680363482]
  We propose a highly scalable hybrid learning model that consists of an RNN learning framework and an attention model. As a novel optimization step, we fit multiple short user sequences in a single RNN pass within a training batch, by solving a greedy knapsack problem on the fly. We also explore the use of off-policy reinforcement learning in multi-session personalized search ranking.
  arXiv  Detail & Related papers  (2022-02-01T06:52:40Z)
• End-to-End User Behavior Retrieval in Click-Through RatePrediction Model [15.52581453176164]
  We propose a locality-sensitive hashing (LSH) method called ETA which can greatly reduce the training and inference cost. 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.
  arXiv  Detail & Related papers  (2021-08-10T06:28:29Z)
• Dynamic Memory based Attention Network for Sequential Recommendation [79.5901228623551]
  We propose a novel long sequential recommendation model called Dynamic Memory-based Attention Network (DMAN) It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users. Based on the dynamic memory, the user's short-term and long-term interests can be explicitly extracted and combined for efficient joint recommendation.
  arXiv  Detail & Related papers  (2021-02-18T11:08:54Z)
• Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction [48.267995749975476]
  In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest. Existing methods mostly utilize attention on the behavior of users, which is not always suitable for CTR prediction. We propose a Multi-Interactive Attention Network (MIAN) to comprehensively extract the latent relationship among all kinds of fine-grained features.
  arXiv  Detail & Related papers  (2020-12-13T05:46:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.