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

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.

Accepted by CIKM 2024

References in corpus (5)

• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
• Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• User Behavior Retrieval for Click-Through Rate Prediction

Cited by in corpus (7)

• MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
• Climber: Toward Efficient Scaling Laws for Large Recommendation Models
• Exploring Scaling Laws of CTR Model for Online Performance Improvement
• Modeling Long-term User Behaviors with Diffusion-driven Multi-interest Network for CTR Prediction
• LREA: Low-Rank Efficient Attention on Modeling Long-Term User Behaviors for CTR Prediction
• MMRM: A Multiplex Multimodal Representation Model for Product Ranking in E-commerce Search
• DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation