发表机构
School of Artificial Intelligence, Jilin University; King Abdullah University of Science and Technology (KAUST); School of Intelligence Science and Technology, Peking University（吉林大学人工智能学院; 阿卜杜拉国王科技大学; 北京大学智能科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究联邦学习中统计异构性问题，从频域视角发现漂移谱偏差，提出SpecGradFilter框架，通过抑制低频信号驯服异构性，实验证明其在高非IID设置下性能优且通信开销小。
AI 中文摘要
联邦学习面临统计异构性挑战，非IID数据引发客户端漂移阻碍全局收敛。现有方法忽视优化信号的内在谱结构。本文从频域视角重新审视客户端漂移，发现漂移谱偏差，提出SpecGradFilter框架，通过抑制不一致低频信号驯服异构性，实验表明其性能优且通信开销小，为鲁棒联邦优化建立新范式。
英文摘要
Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global convergence. While existing approaches attempt to mitigate this drift through spatial-domain gradient correction or regularization, they overlook the intrinsic spectral structure of optimization signals. In this work, we revisit client drift from a novel frequency-domain perspective and uncover a critical Spectral Bias of Drift: inter-client gradient divergence is predominantly concentrated in low-frequency components which encode client-specific distributional shifts, while high-frequency components representing fine-grained features remain relatively consistent. Motivated by this, we propose SpecGradFilter, a unified Spectral Gradient Filtering Framework that tames heterogeneity by suppressing discordant low-frequency signals. Crucially, we demonstrate that SpecGradFilter is a generalizable principle, effective not only via precise FFT-based truncation but also through spatial approximations like Gaussian detrending. Extensive experiments on benchmarks such as CIFAR-10/100 and Tiny-ImageNet demonstrate that SpecGradFilter significantly performs better performance in highly Non-IID settings with negligible communication overhead, establishing a new paradigm for robust federated optimization.
