用条件随机场优化联邦学习权重，提升异构数据下的模型效果
Federated Learning with Energy-Based Structured Probabilistic Inference
- 通过构建客户端的单体与成对势函数，建模客户端可靠性与交互关系
- 在非独立同分布数据下，相比基线方法收敛更快、性能更优
- 适合数据异构严重的场景，尤其适用于医疗、金融等隐私敏感领域
联邦学习通常使用固定或启发式加权规则聚合客户端更新，在客户端数据异质且贡献不同时可能表现不佳。本文提出一种基于条件随机场（CRFs）的框架，为每个客户端定义单体势函数，为所有客户端对定义成对势函数，使服务器能够同时建模客户端的个体可靠性及其相互作用。由此产生的CRF推断生成更优的聚合权重，显著改善全局训练目标的收敛性。实验表明，在非独立同分布（non-IID）异构数据设置下，该方法持续优于多个成熟的联邦学习基线。
原文摘要 · Abstract (English)
Federated learning typically aggregates client updates using fixed or heuristic weighting rules, which can be suboptimal when clients have heterogeneous data and varying contributions to the global model. We propose a framework that refines client aggregation weights using Conditional Random Fields (CRFs). Our method defines unary potentials for individual clients and pairwise potentials for all client pairs, allowing the server to model both client-specific reliability and interactions between clients. The resulting CRF inference produces aggregation weights that enable better convergence of the global training objective. Experiments show that, under non-IID heterogeneity, our approach consistently improves performance over well-established federated learning baselines.
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。