Skip to yearly menu bar Skip to main content

Workshop: Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023 (FL@FM-NeurIPS'23)

MOFL/D: A Federated Multi-objective Learning Framework with Decomposition

Maria Hartmann · GrĂ©goire Danoy · Mohammed Alswaitti · Pascal Bouvry

Keywords: [ multi-objective learning ] [ federated learning ] [ multi-objective optimisation ] [ Multi-objective Machine Learning ]


Multi-objective learning problems occur in all aspects of life and have been studied for decades, including in the field of machine learning. Many such problems also exist in distributed settings, where data cannot easily be shared. In recent years, joint machine learning has been made possible in such settings through the development of the Federated Learning (FL) paradigm. However, no general extension of the FL concept to multi-objective learning has been proposed yet, limiting such problems to non-cooperative individual learning. We address this gap by presenting a first general framework for multi-objective federated learning, based on decomposition (MOFL/D). Our framework addresses the a posteriori type of multi-objective problem, where user preferences are not known during the optimisation process, allowing multiple participants to jointly find a set of solutions, each optimised for some distribution of preferences. We present an instantiation of the framework and validate it through experiments on a set of multi-objective benchmarking problems that are extended from well-known single-objective benchmarks.

Chat is not available.