提出FedHydra框架，统一解决单轮联邦学习中的模型与数据异构问题。
A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
- 采用两阶段学习机制，结合模型分层与异构感知聚合
- 在四个数据集上优于五种前沿方法，跨异构场景表现稳定
- 无需数据即可运行，适合隐私敏感的分布式场景
单轮联邦学习（OSFL）将服务器与客户端间的通信限制为一轮，显著降低通信开销并减少隐私泄露风险，相比传统联邦学习（FL）具有明显优势。然而现有OSFL框架仍易受分布异构影响，因主要关注模型异构而忽略数据异构。为此，我们提出FedHydra——一种统一的、无需数据的单轮联邦学习框架，可有效应对模型与数据双重异构。不同于现有方法，FedHydra引入新颖的两阶段学习机制，通过模型分层和异构感知分层聚合，在学习过程中从不同角度同时监测两类异构问题，从而有效缓解其内在冲突。我们在四个基准数据集上对比了五种SOTA基线方法，结果表明，该方法在同质与异构环境下均优于以往OSFL方法。代码已公开于https://github.com/Jun-B0518/FedHydra。
原文摘要 · Abstract (English)
One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.
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。