Inherent client drifts caused by data heterogeneity, as well as vulnerability to Byzantine attacks within the system, hinder effective model training and convergence in federated learning (FL). This paper presents two new frameworks, named DiveRgence-based Adaptive aGgregation (DRAG) and Byzantine-Resilient DRAG (BR-DRAG), to mitigate client drifts and resist attacks while expediting training. DRAG designs a reference direction and a metric named divergence of degree to quantify the deviation of local updates. Accordingly, each worker can align its local update via linear calibration without extra communication cost. BR-DRAG refines DRAG under Byzantine attacks by maintaining a vetted root dataset at the server to produce trusted reference directions. The workers' updates can be then calibrated to mitigate divergence caused by malicious attacks. We analytically prove that DRAG and BR-DRAG achieve fast convergence for non-convex models under partial worker participation, data heterogeneity, and Byzantine attacks. Experiments validate the effectiveness of DRAG and its superior performance over state-of-the-art methods in handling client drifts, and highlight the robustness of BR-DRAG in maintaining resilience against data heterogeneity and diverse Byzantine attacks.

翻译：数据异质性导致的固有客户端漂移，以及系统对拜占庭攻击的脆弱性，阻碍了联邦学习（FL）中有效的模型训练与收敛。本文提出了两个新框架，分别命名为基于散度的自适应聚合（DRAG）和拜占庭鲁棒DRAG（BR-DRAG），以减轻客户端漂移并抵御攻击，同时加速训练。DRAG设计了一个参考方向和一个名为散度度的度量指标，用以量化本地更新的偏差。相应地，每个工作节点可以通过线性校准来对齐其本地更新，而无需额外的通信开销。BR-DRAG在拜占庭攻击下改进了DRAG，方法是在服务器端维护一个经过审查的根数据集以产生可信的参考方向。随后，工作节点的更新可以被校准，以减轻由恶意攻击引起的散度。我们通过分析证明，在部分工作节点参与、数据异质性和拜占庭攻击的情况下，DRAG和BR-DRAG能够实现非凸模型的快速收敛。实验验证了DRAG在处理客户端漂移方面的有效性及其优于现有先进方法的性能，并突显了BR-DRAG在保持对数据异质性和多种拜占庭攻击的鲁棒性方面的稳健性。