Self evolving memory improves personalized recommendation over time
Self-Evolving Memory for Generative Recommendation
Information RetrievalArtificial Intelligence
Summary
People’s preferences when using recommendation systems change over time, making it hard for these systems to keep up. The authors found that updating one shared model for all users causes popular preferences to overshadow less common ones, leading to poor recommendations for some users. They proposed a new approach called LION that uses a special memory system to separately remember different user patterns and better adapt to changing tastes. This method helps recommendation systems evolve more effectively and fairly over time.
What this means in practice
- •For ecommerce platform teams: Improve product recommendation systems to adapt dynamically to diverse and changing shopper preferences without losing less common tastes.
- •For video streaming service engineers: Tailor content suggestions that evolve with individual viewer trends while preventing dominant viewing habits from overshadowing niche interests.
Authors
Xinyu Lin, Zhuosong Jiang, Zixiao Suo, Siqin Wang, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh, Fei Liu, Wenjie Wang, Fuli Feng, Yang Song, Qifan Wang, Tat-Seng Chua
Abstract
Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolve over time, making self-evolving an essential capability for generative recommender systems. Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters using streaming interactions. Nevertheless, we find that directly applying such strategies to generative recommendation introduces a critical issue, termed evolution conflict. Specifically, heterogeneous preference shifts from different users are optimized within a fully shared autoregressive parameter space, causing dominant behavioral patterns to progressively dominate the model evolution process while underrepresented patterns become increasingly overlooked. To address this issue, we propose a self-evolving memory paradigm for generative recommendation, aiming to enable effective evolution across heterogeneous behavioral patterns. We further identify three key principles for effective self-evolving recommendation systems, including isolated memorization, reinforced evolution, and scalable application. Guided by these principles, we develop LION, a simple yet effective framework centered on a sparse Key-Value memory layer. Specifically, LION introduces sparse memory activation to isolate the evolution of different behavioral patterns, while a consolidation loss is designed to reinforce the learning of underrepresented preference dynamics during continual adaptation. Extensive experiments on diverse real-world datasets demonstrate the effectiveness of LION under various continual evolution settings (e.g., per-period evaluation, user/item group evaluation, and evolution convergence analysis). The codes are released at https://github.com/JazyJiang/Self-Evolving-Memory-for-Generative-Recommendation.