应对数据异构与分布不确定性，提升联邦学习鲁棒性
Distributionally Robust Federated Learning: An ADMM Algorithm
- 引入分布鲁棒优化，增强对数据分布差异的适应能力
- 实验显示在异构数据下性能优于传统联邦学习模型
- 适合面临数据分布不均场景的工业级联邦学习应用
联邦学习（FL）旨在通过分散数据协作训练机器学习模型，避免集中式数据聚合。标准FL模型通常假设所有数据来自同一未知分布，但在实际中，分散数据常表现出异构性。本文提出一种新型联邦学习模型——分布鲁棒联邦学习（DRFL），采用分布鲁棒优化来应对数据异构性和分布模糊性挑战。我们推导出DRFL的可计算重构形式，并基于交替方向乘子法（ADMM）开发了一种新颖求解算法。实验结果表明，当存在数据异构与分布不确定性时，DRFL优于标准联邦学习模型。
原文摘要 · Abstract (English)
Federated learning (FL) aims to train machine learning (ML) models collaboratively using decentralized data, bypassing the need for centralized data aggregation. Standard FL models often assume that all data come from the same unknown distribution. However, in practical situations, decentralized data frequently exhibit heterogeneity. We propose a novel FL model, Distributionally Robust Federated Learning (DRFL), that applies distributionally robust optimization to overcome the challenges posed by data heterogeneity and distributional ambiguity. We derive a tractable reformulation for DRFL and develop a novel solution method based on the alternating direction method of multipliers (ADMM) algorithm to solve this problem. Our experimental results demonstrate that DRFL outperforms standard FL models under data heterogeneity and ambiguity.
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。