用嵌入空间的分布距离,一次聚类解决联邦学习非独立同分布问题。
Clustered Federated Learning via Embedding Distributions
- 基于嵌入空间中数据分布的地球移动距离实现一次性聚类
- 在16个基线和多个挑战性数据集上表现更优
- 适合处理数据异构性强的分布式学习场景
联邦学习(FL)是一种广泛应用于分布式数据环境的机器学习框架,其中客户端持有难以集中化的数据(如出于数据保护原因)。然而,联邦学习易受非独立同分布(non-IID)数据影响。聚类联邦学习通过发现更同质的客户端集群来缓解此问题。本文提出一种新颖的一次性聚类方法 EMD-CFL,利用嵌入空间中数据分布间的地球移动距离(EMD)进行聚类。我们从领域自适应文献中获得理论依据,支持使用EMD,并在大量对比实验中,验证其在16个基线及多种挑战性数据集上的卓越聚类性能。
原文摘要 · Abstract (English)
Federated learning (FL) is a widely used framework for machine learning in distributed data environments where clients hold data that cannot be easily centralised, such as for data protection reasons. FL, however, is known to be vulnerable to non-IID data. Clustered FL addresses this issue by finding more homogeneous clusters of clients. We propose a novel one-shot clustering method, EMD-CFL, using the Earth Mover's distance (EMD) between data distributions in embedding space. We theoretically motivate the use of EMDs using results from the domain adaptation literature and demonstrate empirically superior clustering performance in extensive comparisons against 16 baselines and on a range of challenging datasets.
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。