用互信息损失提升联邦学习公平性，缓解客户间性能差异。
Benchmarking Mutual Information-based Loss Functions in Federated Learning
- 引入互信息损失函数，捕捉客户端数据与模型间的依赖关系。
- 实验显示该方法显著降低客户端间性能差距，提升整体模型效果。
- 适合关注隐私保护下公平性优化的研究者或工业应用者。
联邦学习（FL）因日益增长的隐私关切和如《通用数据保护条例》（GDPR）等法规而受到广泛关注，强调隐私保护与公平机器学习的重要性。在FL中，模型训练在分布式数据上进行，客户端上传本地训练的模型并接收全局聚合模型，无需暴露敏感信息。然而，公平性问题——如偏差、客户端间性能不均以及“搭便车”现象——阻碍了其广泛应用。本文探讨使用互信息（MI）基损失函数来解决这些挑战。MI已被证明是衡量变量间依赖性的强大工具，可优化深度学习模型。通过利用MI提取关键特征并减少偏差，我们旨在提升FL系统的公平性与有效性。通过大规模基准测试，评估了基于MI的损失函数在降低客户端间差异的同时提升整体性能的效果。
原文摘要 · Abstract (English)
Federated Learning (FL) has attracted considerable interest due to growing privacy concerns and regulations like the General Data Protection Regulation (GDPR), which stresses the importance of privacy-preserving and fair machine learning approaches. In FL, model training takes place on decentralized data, so as to allow clients to upload a locally trained model and receive a globally aggregated model without exposing sensitive information. However, challenges related to fairness-such as biases, uneven performance among clients, and the "free rider" issue complicates its adoption. In this paper, we examine the use of Mutual Information (MI)-based loss functions to address these concerns. MI has proven to be a powerful method for measuring dependencies between variables and optimizing deep learning models. By leveraging MI to extract essential features and minimize biases, we aim to improve both the fairness and effectiveness of FL systems. Through extensive benchmarking, we assess the impact of MI-based losses in reducing disparities among clients while enhancing the overall performance of 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。