Learning Evolving Preferences: A Federated Continual Framework for User-Centric Recommendation

2026-03-17

AI Summary

This work addresses the challenges of temporal forgetting and weakened collaborative personalization in federated recommendation systems caused by dynamic shifts in user behavior. To tackle these issues, the authors propose the FCUCR framework, which preserves historical user preferences through a time-aware self-distillation mechanism while enhancing collaborative representation under data heterogeneity via a cross-user prototype transfer strategy—all within a privacy-preserving setting. By integrating federated continual learning, time-aware self-distillation, and user prototype transfer, FCUCR effectively enables long-term personalized recommendations. Extensive experiments on four public benchmarks demonstrate that the proposed framework significantly outperforms existing methods, exhibiting strong compatibility and practical deployment potential.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Consent frameworks and practices on the web

Abstract

User-centric recommendation has become essential for delivering personalized services, as it enables systems to adapt to users' evolving behaviors while respecting their long-term preferences and privacy constraints. Although federated learning offers a promising alternative to centralized training, existing approaches largely overlook user behavior dynamics, leading to temporal forgetting and weakened collaborative personalization. In this work, we propose FCUCR, a federated continual recommendation framework designed to support long-term personalization in a privacy-preserving manner. To address temporal forgetting, we introduce a time-aware self-distillation strategy that implicitly retains historical preferences during local model updates. To tackle collaborative personalization under heterogeneous user data, we design an inter-user prototype transfer mechanism that enriches each client's representation using knowledge from similar users while preserving individual decision logic. Extensive experiments on four public benchmarks demonstrate the superior effectiveness of our approach, along with strong compatibility and practical applicability. Code is available.

Problem

• federated learning
• continual recommendation
• user preference evolution
• temporal forgetting
• collaborative personalization

Innovation

• federated continual learning
• time-aware self-distillation
• inter-user prototype transfer
• user-centric recommendation
• temporal forgetting