提出抗拜占庭攻击的去中心化个性化联邦学习方法，提升模型鲁棒性。
Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration
- 通过邻居方向估计与历史趋势预测，动态修正更新方向。
- 在异构和对抗环境下，性能优于现有最先进方法。
- 适合高风险分布式场景下的个性化模型训练。
本文提出一种稳健的去中心化个性化联邦学习方法R-DPFL，使客户端通过鲁棒的邻居方向估计和基于历史的更新趋势预测，降低拜占庭攻击的影响，而非仅依赖客户端模型聚合。在R-DPFL中，每个客户端首先聚合接收到的邻近更新向量以计算当前轮次的模型更新；随后基于历史值和本地模型变化预测该更新应有值；最后计算两者差值，自适应裁剪后加入本地更新。通过严格分析证明了学习过程的收敛性，表明诚实客户端在拜占庭邻居干扰下仍能保持稳定的个性化下降动力学，且无需邻近模型间达成共识。在CIFAR-10上的大量实验显示，R-DPFL在异构和对抗设置下持续优于现有的去中心化及个性化联邦学习基线。
原文摘要 · Abstract (English)
This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attacks via robust neighborhood direction estimation and history-based update trend prediction, rather than purely aggregating client models as in the existing work. In R-DPFL, each client first computes the current-round model update by aggregating the received neighborhood update vectors. It then predicts what this update should be based on its historical values and local model changes. Finally, R-DPFL computes the difference between these two quantities, adaptively clips this difference, and adds it to the local update. We prove convergence of the learning process through rigorous analysis and show that honest clients maintain stable personalized descent dynamics under Byzantine neighbor perturbations without requiring consensus among neighboring models. Extensive experiments on CIFAR-10 demonstrate that RDPFL consistently outperforms state-of-the-art decentralized and personalized federated learning baselines under heterogeneous and adversarial settings.
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。