Towards Fair Federated Learning with Zero-Shot Data Augmentation
arXiv:2104.13417
Abstract
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. Although it is recognized that statistical heterogeneity of the client local data yields slower global model convergence, it is less commonly recognized that it also yields a biased federated global model with a high variance of accuracy across clients. In this work, we aim to provide federated learning schemes with improved fairness. To tackle this challenge, we propose a novel federated learning system that employs zero-shot data augmentation on under-represented data to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks. We study two variants of this scheme, Fed-ZDAC (federated learning with zero-shot data augmentation at the clients) and Fed-ZDAS (federated learning with zero-shot data augmentation at the server). Empirical results on a suite of datasets demonstrate the effectiveness of our methods on simultaneously improving the test accuracy and fairness.
arXiv commentAccepted by IEEE CVPR Workshop on Fair, Data Efficient And Trusted Computer Vision
References in corpus (12)
- Deep Learning with Differential Privacy
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning with Non-IID Data
- Federated Learning with Personalization Layers
- Differentially Private Federated Learning: A Client Level Perspective
- Federated Optimization in Heterogeneous Networks
- Fair Resource Allocation in Federated Learning
- Overcoming Forgetting in Federated Learning on Non-IID Data
- Variational Federated Multi-Task Learning
- Universal Neural Machine Translation for Extremely Low Resource Languages
- Federated Learning via Synthetic Data