Client Adaptation improves Federated Learning with Simulated Non-IID Clients
arXiv:2007.04806
Abstract
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.
11 pages, 11 figures. To appear at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020
References in corpus (9)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Federated Learning: Strategies for Improving Communication Efficiency
- Conditional Image Generation with PixelCNN Decoders
- Federated Learning with Non-IID Data
- How To Backdoor Federated Learning
- Federated Adversarial Domain Adaptation
- General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline