Improving Fairness via Federated Learning

Abstract

Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is federated learning necessary, i.e., can we simply train locally fair classifiers and aggregate them? In this work, we first propose a new theoretical framework, with which we demonstrate that federated learning can strictly boost model fairness compared with such non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse than that of a fair classifier trained on centralized data. To bridge this gap, we propose FedFB, a private fair learning algorithm on decentralized data. The key idea is to modify the FedAvg protocol so that it can effectively mimic the centralized fair learning. Our experimental results show that FedFB significantly outperforms existing approaches, sometimes matching the performance of the centrally trained model.

arXiv comment39 pages, 7 figures

References in corpus (13)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Equality of Opportunity in Supervised Learning
• Towards Federated Learning at Scale: System Design
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• On the (im)possibility of fairness
• Agnostic Federated Learning
• A Field Guide to Federated Optimization
• Identifying and Correcting Label Bias in Machine Learning
• From Parity to Preference-based Notions of Fairness in Classification
• Hierarchically Fair Federated Learning
• Enforcing fairness in private federated learning via the modified method of differential multipliers
• Training Fair Models in Federated Learning without Data Privacy Infringement

Cited by in corpus (4)

• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Training Fair Models in Federated Learning without Data Privacy Infringement
• Fairness-aware Federated Minimax Optimization with Convergence Guarantee
• Models of fairness in federated learning