Fairness-aware Agnostic Federated Learning

Abstract

Federated learning is an emerging framework that builds centralized machine learning models with training data distributed across multiple devices. Most of the previous works about federated learning focus on the privacy protection and communication cost reduction. However, how to achieve fairness in federated learning is under-explored and challenging especially when testing data distribution is different from training distribution or even unknown. Introducing simple fairness constraints on the centralized model cannot achieve model fairness on unknown testing data. In this paper, we develop a fairness-aware agnostic federated learning framework (AgnosticFair) to deal with the challenge of unknown testing distribution. We use kernel reweighing functions to assign a reweighing value on each training sample in both loss function and fairness constraint. Therefore, the centralized model built from AgnosticFair can achieve high accuracy and fairness guarantee on unknown testing data. Moreover, the built model can be directly applied to local sites as it guarantees fairness on local data distributions. To our best knowledge, this is the first work to achieve fairness in federated learning. Experimental results on two real datasets demonstrate the effectiveness in terms of both utility and fairness under data shift scenarios.

arXiv comment12 pages, 3 figures

References in corpus (12)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning with Non-IID Data
• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
• Three Approaches for Personalization with Applications to Federated Learning
• Agnostic Federated Learning
• Fairness Without Demographics in Repeated Loss Minimization
• Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
• Learning Non-Discriminatory Predictors
• Distributed Mean Estimation with Limited Communication
• AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training
• Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients