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

TL;DR

This paper provides a comprehensive survey and taxonomy of how multi-objective optimization techniques are integrated into Federated Learning, highlighting current methods, challenges, and future research directions.

Contribution

It offers the first systematic overview and taxonomy of multi-objective methods in Federated Learning, categorizing existing approaches and guiding future research.

Findings

Proposed a taxonomy categorizing multi-objective federated methods.

Surveyed state-of-the-art approaches and identified key challenges.

Outlined future research directions in the field.

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.