论文标题
最佳对联合学习的重要性抽样
Optimal Importance Sampling for Federated Learning
论文作者
论文摘要
联合学习涉及集中式和分散的处理任务的混合物，在该任务中，服务器会定期选择代理样本，然后这些又要对其本地数据进行采样以计算其学习更新的随机梯度。此过程不断运行。代理和数据的采样通常都是均匀的。但是，在这项工作中，我们考虑采样不均匀。我们为代理和数据选择提供了最佳的重要性采样策略，并表明不替换的非均匀采样可改善原始FedAvg算法的性能。我们对回归和分类问题进行实验，以说明理论结果。
Federated learning involves a mixture of centralized and decentralized processing tasks, where a server regularly selects a sample of the agents and these in turn sample their local data to compute stochastic gradients for their learning updates. This process runs continually. The sampling of both agents and data is generally uniform; however, in this work we consider non-uniform sampling. We derive optimal importance sampling strategies for both agent and data selection and show that non-uniform sampling without replacement improves the performance of the original FedAvg algorithm. We run experiments on a regression and classification problem to illustrate the theoretical results.
