发表机构
Faculty of Applied Sciences, Macao Polytechnic University; School of Engineering and Technology, Central Queensland University; School of Information and Communication Technology, Griffith University（澳门理工大学应用科学学院; 中央昆士兰大学工程与技术学院; 格里菲斯大学信息与通信技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出鲁棒去中心化个性化联邦学习方法R-DPFL，通过邻域方向估计和基于历史的更新趋势预测抵御拜占庭攻击，在CIFAR-10上优于现有基线。
AI 中文摘要
本文提出了一种鲁棒的去中心化个性化联邦学习方法R-DPFL，该方法通过鲁棒的邻域方向估计和基于历史信息的更新趋势预测，使客户端能够减少拜占庭攻击的影响，而非像现有工作那样纯粹聚合客户端模型。在R-DPFL中，每个客户端首先通过聚合接收到的邻域更新向量来计算当前轮的模型更新。然后，它基于历史值和本地模型变化来预测该更新应有的值。最后，R-DPFL计算这两个量之间的差异，自适应地裁剪该差异，并将其添加到本地更新中。我们通过严格的分析证明了学习过程的收敛性，并表明在拜占庭邻居扰动下，诚实客户端无需邻居模型达成共识即可保持稳定的个性化下降动态。在CIFAR-10上的大量实验表明，在异构和对抗性设置下，R-DPFL始终优于最先进的去中心化和个性化联邦学习基线。
英文摘要
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.
