Similarity-Aware Personalized Federated Learning in Heterogeneous Environments

2026-09-02

AI Summary

为解决联邦学习中因客户端数据分布不匹配导致的性能下降问题，提出SAPE-FL方法，通过结合全局模型和基于相似度加权的对等平均模型，提高异构环境下的个性化模型性能。

Abstract

Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch across clients often leads to poor global generalization and degraded local client-level performance. In such scenarios, some of the clients with their local models trained solely on local data may perform better than the globally learnt model, thus nullifying the benefits of collaborative federated learning. To address this, we propose SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model. By incorporating dynamic, client-specific regularization based on both model similarity and output similarity, SAPE-FL adaptively balances global knowledge transfer and peer collaboration while filtering out dissimilar clients. This dual anchoring mitigates negative transfer and enhances robustness in heterogeneous settings. We theoretically analyze our algorithm establishing its convergence guarantees and empirically show that SAPE-FL outperforms state-of-the-art methods under high statistical heterogeneity and low client data regimes.

Problem

• Federated Learning
• Heterogeneous Environments
• Distribution Mismatch
• Global Generalization
• Local Performance

Innovation

• Similarity-Aware
• Personalized Federated Learning
• Dual Anchoring
• Dynamic Regularization
• Heterogeneous Environments