Device Heterogeneity in Federated Learning: A Superquantile Approach
From MaRDI portal
Publication:6335570
arXiv2002.11223MaRDI QIDQ6335570
Author name not available (Why is that?)
Publication date: 25 February 2020
Abstract: We propose a federated learning framework to handle heterogeneous client devices which do not conform to the population data distribution. The approach hinges upon a parameterized superquantile-based objective, where the parameter ranges over levels of conformity. We present an optimization algorithm and establish its convergence to a stationary point. We show how to practically implement it using secure aggregation by interleaving iterations of the usual federated averaging method with device filtering. We conclude with numerical experiments on neural networks as well as linear models on tasks from computer vision and natural language processing.
Has companion code repository: https://github.com/krishnap25/simplicial-fl
This page was built for publication: Device Heterogeneity in Federated Learning: A Superquantile Approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6335570)
