Personalized Federated Recommendation With Knowledge Guidance

2025-11-16

AI Summary

Existing federated recommendation (FedRec) methods struggle to balance personalization and memory efficiency: single-knowledge models lose user-specific patterns due to coarse-grained knowledge replacement, while dual-knowledge models incur prohibitive memory overhead. This paper proposes FedRKG, a framework that achieves dual-knowledge-level performance under the memory constraints of a single-knowledge architecture. Its core innovations are: (1) a knowledge-guided mechanism that incorporates global knowledge into local embeddings without fully overwriting them—thereby preserving personalized representations; and (2) a fine-grained adaptive guidance strategy that dynamically modulates the knowledge fusion strength for each user-item interaction. FedRKG is model-agnostic and lightweight for deployment. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, validating its effectiveness in enhancing recommendation accuracy under stringent memory budgets.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Federated Recommendation (FedRec) has emerged as a key paradigm for building privacy-preserving recommender systems. However, existing FedRec models face a critical dilemma: memory-efficient single-knowledge models suffer from a suboptimal knowledge replacement practice that discards valuable personalization, while high-performance dual-knowledge models are often too memory-intensive for practical on-device deployment. We propose Federated Recommendation with Knowledge Guidance (FedRKG), a model-agnostic framework that resolves this dilemma. The core principle, Knowledge Guidance, avoids full replacement and instead fuses global knowledge into preserved local embeddings, attaining the personalization benefits of dual-knowledge within a single-knowledge memory footprint. Furthermore, we introduce Adaptive Guidance, a fine-grained mechanism that dynamically modulates the intensity of this guidance for each user-item interaction, overcoming the limitations of static fusion methods. Extensive experiments on benchmark datasets demonstrate that FedRKG significantly outperforms state-of-the-art methods, validating the effectiveness of our approach. The code is available at https://github.com/Jaehyung-Lim/fedrkg.

Problem

• Resolving memory-efficient single-knowledge models' suboptimal knowledge replacement practice
• Addressing high-performance dual-knowledge models' memory-intensive on-device deployment issues
• Overcoming static fusion limitations in personalized federated recommendation systems

Innovation

• Fuses global knowledge into local embeddings
• Uses adaptive guidance for user-item interactions
• Achieves dual-knowledge performance with single-memory footprint