通过方差正则化提升联邦学习中各客户端的性能公平性
FAIRVAR: Fair Federated Learning via Variance Regularization
- 引入梯度方差正则化，设计两种变体提升公平性
- 在异构数据下显著降低客户端准确率方差，平均性能不降
- 适合关注模型公平性的联邦学习研究与应用者
联邦学习（FL）允许多方协作训练模型而无需共享原始数据。然而，数据异构性可能导致某些客户端对全局模型产生过大的影响，造成性能差异。公平性指减少此类差异，是联邦学习中的关键问题。本文研究性能均衡公平性，目标是最小化客户端间的性能差距。我们评估了多种现有公平性方法，并提出一种新的梯度方差正则化方法，实现为FairGrad（近似）和FairGrad*（精确）两种变体。理论上分析了其与已有方法的联系；在异构基准上实证表明，FairGrad与FairGrad*能持续改善公平性，降低客户端准确率方差，同时保持或优于现有公平性基线的平均性能。
原文摘要 · Abstract (English)
Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the global model, leading to disparities in their performance. Fairness, understood as reducing these disparities, is therefore a crucial concern in FL and has been addressed in various ways. We studied performance equitable fairness in FL, where the goal is to minimize performance disparities across clients. We evaluated several existing fairness-aware methods and introduce here a new gradient-variance-regularized method, implemented in two variants: FairGrad (approximate) and FairGrad* (exact). We theoretically characterize the connections between these methods and, empirically, on heterogeneous benchmarks, show that FairGrad and FairGrad* consistently improve fairness by reducing variance in client accuracies, while maintaining competitive or improved mean performance compared to existing fairness-aware baselines.
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。