用生成模型在本地补全缺失类别，缓解联邦学习中的标签不平衡问题。
Recovering Global Data Distribution Locally in Federated Learning
- 客户端用生成模型合成少数和缺失类别的图像以补全数据分布。
- 通过本地真实数据自适应微调生成过程，使合成数据更贴近全局分布。
- 全程在本地完成，保护隐私且显著提升分类性能。
联邦学习（FL）是一种分布式机器学习范式，允许多个客户端协作训练共享模型而无需共享原始数据。然而，其主要挑战之一是标签不平衡：某些客户端可能仅拥有特定类别，导致大量少数类和缺失类。现有工作集中于优化本地更新或全局聚合，却忽略了客户端间存在的不平衡标签分布。本文提出一种新方法 ReGL，核心思想是在本地恢复全局数据分布。具体而言，每个客户端使用生成模型合成少数和缺失类别的图像，以缓解标签不平衡。此外，通过本地真实数据自适应微调生成过程，使合成图像更贴近全局分布。重要的是，生成与微调均在客户端侧完成，不泄露数据隐私。在多个图像分类数据集上的全面实验表明，该方法在根本性解决联邦学习中标签不平衡问题方面显著优于现有最先进方法。
原文摘要 · Abstract (English)
Federated Learning (FL) is a distributed machine learning paradigm that enables collaboration among multiple clients to train a shared model without sharing raw data. However, a major challenge in FL is the label imbalance, where clients may exclusively possess certain classes while having numerous minority and missing classes. Previous works focus on optimizing local updates or global aggregation but ignore the underlying imbalanced label distribution across clients. In this paper, we propose a novel approach ReGL to address this challenge, whose key idea is to Recover the Global data distribution Locally. Specifically, each client uses generative models to synthesize images that complement the minority and missing classes, thereby alleviating label imbalance. Moreover, we adaptively fine-tune the image generation process using local real data, which makes the synthetic images align more closely with the global distribution. Importantly, both the generation and fine-tuning processes are conducted at the client-side without leaking data privacy. Through comprehensive experiments on various image classification datasets, we demonstrate the remarkable superiority of our approach over existing state-of-the-art works in fundamentally tackling label imbalance in FL.
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。