Client Adaptation improves Federated Learning with Simulated Non-IID\n Clients

2020/07/09 by Laura Rieger, Rieger, Laura, Rasmus M. Th. Høegh +3
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #MRI in cancer diagnosis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2007.04806

openalex publication_date 2020/07/09 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28

Abstract

We present a federated learning approach for learning a client adaptable,\nrobust model when data is non-identically and non-independently distributed\n(non-IID) across clients. By simulating heterogeneous clients, we show that\nadding learned client-specific conditioning improves model performance, and the\napproach is shown to work on balanced and imbalanced data set from both audio\nand image domains. The client adaptation is implemented by a conditional gated\nactivation unit and is particularly beneficial when there are large differences\nbetween the data distribution for each client, a common scenario in federated\nlearning.\n

Citations

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• How To Backdoor Federated Learning
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis
• Learning Multiple Layers of Features from Tiny Images

Related

• Federated Residual Learning
• FedImpro: Measuring and Improving Client Update in Federated Learning
• Federated Learning with Server Learning: Enhancing Performance for Non-IID Data
• FedCliP: Federated Learning with Client Pruning
• Towards Instance-adaptive Inference for Federated Learning