解决联邦学习中异构数据导致的性能下降问题。
Similarity-Aware Personalized Federated Learning in Heterogeneous Environments
- 基于模型与输出相似性动态调整各客户端的正则化强度。
- 在高异构性和小数据场景下，性能优于现有方法。
- 适合数据分布差异大、参与方少的现实联邦学习场景。
联邦学习（FL）使分布式客户端在保护数据隐私的前提下协同训练模型。然而，客户端间的数据分布差异常导致全局模型泛化能力差，且本地性能下降。在这种情况下，仅使用本地数据训练的某些客户端模型性能反而优于全局模型，削弱了协作优势。为此，我们提出SAPE-FL（相似性感知个性化联邦学习），一种新型个性化框架，将每个客户端模型同时锚定于全局模型和一个基于相似性的同伴平均模型。通过结合模型相似性和输出相似性的动态、客户端特定正则化，SAPE-FL自适应平衡全局知识迁移与同伴协作，同时过滤不相似客户端。双重锚定机制缓解了负向迁移，在异构环境中增强鲁棒性。我们从理论上分析了算法的收敛性，并在实验中验证：在高统计异构性和低客户端数据条件下，SAPE-FL优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。