用贝叶斯混合方法提升单轮联邦学习效果
FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
- 基于贝叶斯混合拉普拉斯近似建模客户端后验分布
- 在多个数据集上优于依赖单峰近似的基线方法
- 适合追求高效单轮协同学习的场景
单轮联邦学习（One-Shot FL）是一种新兴范式，允许多个客户端在与中心服务器的一次通信中协同训练全局模型。本文从贝叶斯推断视角分析该问题，提出FedBEns算法，利用本地损失函数的多模态特性寻找更优全局模型。该方法通过拉普拉斯近似构建客户端局部后验的混合分布，由服务器聚合以推断全局模型。我们在多个数据集上进行了广泛实验，结果表明，所提方法显著优于依赖局部损失单峰近似的现有基线。
原文摘要 · Abstract (English)
One-Shot Federated Learning (FL) is a recent paradigm that enables multiple clients to cooperatively learn a global model in a single round of communication with a central server. In this paper, we analyze the One-Shot FL problem through the lens of Bayesian inference and propose FedBEns, an algorithm that leverages the inherent multimodality of local loss functions to find better global models. Our algorithm leverages a mixture of Laplace approximations for the clients' local posteriors, which the server then aggregates to infer the global model. We conduct extensive experiments on various datasets, demonstrating that the proposed method outperforms competing baselines that typically rely on unimodal approximations of the local losses.
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。