We present a federated learning approach for learning a client adaptable, robust model when data is non-identically and non-independently distributed (non-IID) across clients. By simulating heterogeneous clients, we show that adding learned client-specific conditioning improves model performance, and the approach is shown to work on balanced and imbalanced data set from both audio and image domains. The client adaptation is implemented by a conditional gated activation unit and is particularly beneficial when there are large differences between the data distribution for each client, a common scenario in federated learning.
@article{arxiv.2007.04806,
title = {Client Adaptation improves Federated Learning with Simulated Non-IID Clients},
author = {Laura Rieger and Rasmus M. Th. Høegh and Lars K. Hansen},
journal= {arXiv preprint arXiv:2007.04806},
year = {2020}
}
Comments
11 pages, 11 figures. To appear at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020