通过高斯权重机制提升联邦学习聚类质量，改善异构数据下的模型性能。
Interaction-Aware Gaussian Weighting for Clustered Federated Learning
- 用高斯奖励机制衡量客户端间交互，动态分组相似数据分布的客户端。
- 在多个基准数据集上，聚类质量与分类准确率均优于现有方法。
- 适合处理数据异构性强、存在类别不平衡的分布式学习场景。
联邦学习（FL）作为一种去中心化范式，在保护隐私的同时训练模型。然而，传统联邦学习面临数据异构性和类别不平衡问题，导致模型性能下降。聚类联邦学习通过将具有相似数据分布的客户端分组，在保持个性化与去中心化训练之间取得平衡，有效缓解了异构性带来的负面影响。本文提出一种新型聚类联邦学习方法FedGWC（Federated Gaussian Weighting Clustering），基于客户端数据分布进行分组，实现更鲁棒且个性化的模型训练。FedGWC通过将个体经验损失转换为高斯奖励机制，识别出同质聚类；同时引入Wasserstein Adjusted Score作为新的聚类评估指标，衡量聚类内部关于各类别分布的一致性。实验在多个基准数据集上表明，FedGWC在聚类质量与分类准确率方面均优于现有联邦学习算法，验证了该方法的有效性。
原文摘要 · Abstract (English)
Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach.
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。