单轮完成联邦学习聚类与训练，解决非独立同分布数据挑战
Single-Round Clustered Federated Learning via Data Collaboration Analysis for Non-IID Data
- 基于数据协作分析，仅用一轮通信完成客户端聚类与模型训练
- 在多个非独立同分布数据集上达到与多轮方法相当的准确率
- 适合通信资源受限场景，如移动设备或隐私要求高的应用
联邦学习（FL）可在不共享原始数据的前提下实现跨客户端的分布式学习。当客户端间存在严重统计异质性时，聚类联邦学习（CFL）通过将相似客户端分组并训练簇级模型来提升性能。然而，多数CFL方法依赖多轮通信进行聚类估计和模型更新，在通信轮数受限时实用性受限。本文提出基于数据协作分析的单轮聚类联邦学习（DC-CFL），仅利用数据协作分析中共享的信息，即可完成客户端聚类与簇级学习。DC-CFL通过标签分布之间的总变差距离量化客户端间相似性，采用层次聚类进行聚类估计，并通过数据协作分析实现簇级学习。在多个公开数据集上，针对典型非独立同分布条件的实验表明，DC-CFL仅需一轮通信即可达到与多轮基线相当的准确率。结果表明，当多轮通信不可行时，DC-CFL是协同人工智能模型开发的实用替代方案。源代码已公开于 https://github.com/souta-suga/DC-CFL。
原文摘要 · Abstract (English)
Federated Learning (FL) enables distributed learning across multiple clients without sharing raw data. When statistical heterogeneity across clients is severe, Clustered Federated Learning (CFL) can im-prove performance by grouping similar clients and training cluster-wise models. However, most CFL approaches rely on multiple communication rounds for cluster estimation and model updates, which limits their practicality under tight constraints on communication rounds. We propose Data Collaboration-based Clustered Federated Learning (DC-CFL), a single-round framework that completes both client clustering and cluster-wise learning, using only the information shared in DC analysis. DC-CFL quantifies inter-client similarity via total variation distance between label distributions, estimates clusters using hierarchical clustering, and performs cluster-wise learning via DC analysis. Experiments on multiple open datasets under representative non-IID conditions show that DC-CFL achieves accuracy comparable to multi-round baselines while requiring only one communication round. These results indicate that DC-CFL is a practical alternative for collaborative AI model development when multiple communication rounds are impractical. Our source code is publicly available at https://github.com/souta-suga/DC-CFL.
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。