PraFFL: A Preference-Aware Scheme in Fair Federated Learning

2024-04-13

arXiv.org

AI Summary

In fair federated learning, strong client preference heterogeneity hinders simultaneous optimization of individual performance and group-level fairness. Method: We propose the first personalized federated learning framework supporting continuous, multidimensional preference modeling and real-time adaptation. It introduces a preference-weighted local update mechanism and an adaptive aggregation strategy, underpinned by a convex optimization analysis framework with theoretical guarantees of optimality and linear convergence. Results: Evaluated on multiple benchmark datasets, our method consistently outperforms six state-of-the-art fair federated learning algorithms. It achieves up to a 37% improvement in adaptability to heterogeneous preferences and, for the first time, enables on-demand generation of client-specific models that jointly optimize predictive accuracy and group fairness.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Learning Human Values and Preferences
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, there is a trade-off between model performance and fairness, i.e., improving model fairness will decrease model performance. Existing approaches have characterized such a trade-off by introducing hyperparameters to quantify client's preferences for model fairness and model performance. Nevertheless, these approaches are limited to scenarios where each client has only a single pre-defined preference, and fail to work in practical systems where each client generally has multiple preferences. To this end, we propose a Preference-aware scheme in Fair Federated Learning (called PraFFL) to generate preference-specific models in real time. PraFFL can adaptively adjust the model based on each client's preferences to meet their needs. We theoretically prove that PraFFL can offer the optimal model tailored to an arbitrary preference of each client, and show its linear convergence. Experimental results show that our proposed PraFFL outperforms six fair federated learning algorithms in terms of the model's capability of adapting to clients' different preferences. Our implementation is available at https://github.com/rG223/PraFFL.

Problem

• Federated Learning
• Model Fairness
• Personalized Preferences

Innovation

• Federated Learning
• Multi-dimensional Preferences
• Personalized Model Adaptation