解决联邦学习异构数据下的性能下降问题，通过客户端本地正则化提升模型泛化能力。
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data
- 在客户端直接引入分布对齐正则化，避免依赖全局模型调整。
- 在多个数据集上准确率显著优于现有方法，最高提升3.2%。
- 适合资源受限场景，计算开销低，易于实际部署。
联邦学习在面对非独立同分布（non-IID）数据时常出现性能严重下降，主要源于局部分类器偏差。传统方法如全局模型正则化或层冻结要么计算成本高，要么难以适应特征偏移。本文提出UniVarFL，一种新型联邦学习框架，在客户端层面直接模拟独立同分布（IID）训练动态，无需依赖全局模型。该框架在本地训练中引入两种互补正则化策略：分类器方差正则化，使类别概率分布逼近IID预期，有效缓解局部分类器偏差；超球面均匀性正则化，促使特征表示在超球面上均匀分布，增强模型在多样化数据分布下的泛化能力。在多个基准数据集上的大量实验表明，UniVarFL在准确率上显著优于现有方法，展现出在真实世界联邦学习部署中的高可扩展性和高效性，尤其适用于资源受限环境。代码已开源。
原文摘要 · Abstract (English)
Federated Learning (FL) often suffers from severe performance degradation when faced with non-IID data, largely due to local classifier bias. Traditional remedies such as global model regularization or layer freezing either incur high computational costs or struggle to adapt to feature shifts. In this work, we propose UniVarFL, a novel FL framework that emulates IID-like training dynamics directly at the client level, eliminating the need for global model dependency. UniVarFL leverages two complementary regularization strategies during local training: Classifier Variance Regularization, which aligns class-wise probability distributions with those expected under IID conditions, effectively mitigating local classifier bias; and Hyperspherical Uniformity Regularization, which encourages a uniform distribution of feature representations across the hypersphere, thereby enhancing the model's ability to generalize under diverse data distributions. Extensive experiments on multiple benchmark datasets demonstrate that UniVarFL outperforms existing methods in accuracy, highlighting its potential as a highly scalable and efficient solution for real-world FL deployments, especially in resource-constrained settings. Code: https://github.com/sunnyinAI/UniVarFL
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。