Multi-objective methods in Federated Learning: A survey and taxonomy

2025-02-05

AI Summary

Federated learning (FL) faces inherent trade-offs among fairness, model utility, and resource efficiency—conflicting objectives that hinder holistic optimization. To address this, this work pioneers the systematic integration of multi-objective optimization (MOO) with FL, proposing the first unified taxonomy for this interdisciplinary domain. The taxonomy is structured along three dimensions: objective coupling, MOO strategies—including Pareto-frontier search, weighted-sum aggregation, and constraint-based methods—and client heterogeneity. A comprehensive survey of state-of-the-art approaches identifies five dominant research paradigms and rigorously defines key conceptual labels, thereby bridging a longstanding gap between MOO and FL communities. The framework establishes foundational principles for method design, standardized evaluation protocols, and future theoretical and empirical investigations in multi-objective federated learning.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The Federated Learning paradigm facilitates effective distributed machine learning in settings where training data is decentralized across multiple clients. As the popularity of the strategy grows, increasingly complex real-world problems emerge, many of which require balancing conflicting demands such as fairness, utility, and resource consumption. Recent works have begun to recognise the use of a multi-objective perspective in answer to this challenge. However, this novel approach of combining federated methods with multi-objective optimisation has never been discussed in the broader context of both fields. In this work, we offer a first clear and systematic overview of the different ways the two fields can be integrated. We propose a first taxonomy on the use of multi-objective methods in connection with Federated Learning, providing a targeted survey of the state-of-the-art and proposing unambiguous labels to categorise contributions. Given the developing nature of this field, our taxonomy is designed to provide a solid basis for further research, capturing existing works while anticipating future additions. Finally, we outline open challenges and possible directions for further research.

Problem

• Federated Learning with multi-objective optimization
• Balancing fairness, utility, and resource consumption
• Taxonomy for integrating multi-objective methods

Innovation

• Multi-objective optimization in Federated Learning
• Taxonomy for integrating conflicting demands
• Survey of state-of-the-art methods