通过激活聚类实现公平联邦学习，缓解客户端偏见问题。
Equitable Federated Learning with Activation Clustering
- 基于激活向量构建相似度矩阵，对客户端进行聚类分组。
- 提出加权机制使各聚类贡献均衡，收敛速度达O(1/√K)。
- 有效降低不同客户端间的算法偏见，适合存在数据异质性的场景。
联邦学习是一种重要的分布式学习范式，能促进多方协作、保持数据本地化并保障隐私。然而，各客户端在数据生成过程中存在技术、文化等多方面偏差，现有方法常忽略这种异质性，反而加剧对某些群体的偏见。为此，本文提出一种基于激活聚类的公平联邦学习框架：根据客户端间激活向量的相似性进行聚类，并设计独特的相似度矩阵构建方式；进一步提出客户端加权机制，确保每个聚类获得同等重要性，理论证明可达到O(1/√K)的收敛速率，实现ε-驻点解。在多个基线方法上的实验表明，该方法显著降低了客户端聚类间的偏差，从而有效缓解了针对特定群体的算法偏见。
原文摘要 · Abstract (English)
Federated learning is a prominent distributed learning paradigm that incorporates collaboration among diverse clients, promotes data locality, and thus ensures privacy. These clients have their own technological, cultural, and other biases in the process of data generation. However, the present standard often ignores this bias/heterogeneity, perpetuating bias against certain groups rather than mitigating it. In response to this concern, we propose an equitable clustering-based framework where the clients are categorized/clustered based on how similar they are to each other. We propose a unique way to construct the similarity matrix that uses activation vectors. Furthermore, we propose a client weighing mechanism to ensure that each cluster receives equal importance and establish $O(1/\sqrt{K})$ rate of convergence to reach an $ε-$stationary solution. We assess the effectiveness of our proposed strategy against common baselines, demonstrating its efficacy in terms of reducing the bias existing amongst various client clusters and consequently ameliorating algorithmic bias against specific groups.
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。