Unified Group Fairness on Federated Learning

Abstract

Federated learning (FL) has emerged as an important machine learning paradigm where a global model is trained based on the private data from distributed clients. However, most of existing FL algorithms cannot guarantee the performance fairness towards different groups because of data distribution shift over groups. In this paper, we formulate the problem of unified group fairness on FL, where the groups can be formed by clients (including existing clients and newly added clients) and sensitive attribute(s). To solve this problem, we first propose a general fair federated framework. Then we construct a unified group fairness risk from the view of federated uncertainty set with theoretical analyses to guarantee unified group fairness on FL. We also develop an efficient federated optimization algorithm named Federated Mirror Descent Ascent with Momentum Acceleration (FMDA-M) with convergence guarantee. We validate the advantages of the FMDA-M algorithm with various kinds of distribution shift settings in experiments, and the results show that FMDA-M algorithm outperforms the existing fair FL algorithms on unified group fairness.

References in corpus (17)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Equality of Opportunity in Supervised Learning
• Federated Learning with Non-IID Data
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Agnostic Federated Learning
• Learning Non-Discriminatory Predictors
• Distributed Mean Estimation with Limited Communication
• Federated Learning with Only Positive Labels
• Distributionally Robust Federated Averaging
• Stable Adversarial Learning under Distributional Shifts
• Beyond Individual and Group Fairness
• Communication-Efficient Agnostic Federated Averaging
• Federated Learning with Fair Averaging

Cited by in corpus (1)

• Models of fairness in federated learning