Federated learning (FL) is a privacy-preserving paradigm for collaboratively training a global model from decentralized clients. However, the performance of FL is hindered by non-independent and identically distributed (non-IID) data and device heterogeneity. In this work, we revisit this key challenge through the lens of gradient conflicts on the server side. Specifically, we first investigate the gradient conflict phenomenon among multiple clients and reveal that stronger heterogeneity leads to more severe gradient conflicts. To tackle this issue, we propose FedGH, a simple yet effective method that mitigates local drifts through Gradient Harmonization. This technique projects one gradient vector onto the orthogonal plane of the other within conflicting client pairs. Extensive experiments demonstrate that FedGH consistently enhances multiple state-of-the-art FL baselines across diverse benchmarks and non-IID scenarios. Notably, FedGH yields more significant improvements in scenarios with stronger heterogeneity. As a plug-and-play module, FedGH can be seamlessly integrated into any FL framework without requiring hyperparameter tuning.

翻译：联邦学习（FL）是一种通过分散客户端协作训练全局模型的隐私保护范式。然而，非独立同分布（non-IID）数据和设备异构性会阻碍FL的性能。本文从服务器端梯度冲突的视角重新审视这一关键挑战。具体而言，我们首先研究了多客户端间的梯度冲突现象，揭示出更强的异构性会导致更严重的梯度冲突。为解决该问题，我们提出FedGH——一种通过梯度协调（Gradient Harmonization）缓解局部漂移的简洁有效方法。该技术将冲突客户端对中一个梯度向量投影到另一个梯度向量的正交平面上。大量实验表明，FedGH能在不同基准数据集和非独立同分布场景下持续提升多种最先进的FL基线方法性能。值得注意的是，在异构性更强的场景中，FedGH带来的性能提升更为显著。作为即插即用模块，FedGH无需超参数调优即可无缝集成到任何FL框架中。