Towards Fairness-Aware Multi-Objective Optimization

Abstract

Recent years have seen the rapid development of fairness-aware machine learning in mitigating unfairness or discrimination in decision-making in a wide range of applications. However, much less attention has been paid to the fairness-aware multi-objective optimization, which is indeed commonly seen in real life, such as fair resource allocation problems and datadriven multi-objective optimization problems. This paper aims to illuminate and broaden our understanding of multi-objective optimization from the perspective of fairness. To this end, we start with a discussion of user preferences in multi-objective optimization and then explore its relationship to fairness in machine learning and multi-objective optimization. Following the above discussions, representative cases of fairness-aware multiobjective optimization are presented, further elaborating the importance of fairness in traditional multi-objective optimization, data-driven optimization and federated optimization. Finally, challenges and opportunities in fairness-aware multi-objective optimization are addressed. We hope that this article makes a small step forward towards understanding fairness in the context of optimization and promote research interest in fairness-aware multi-objective optimization.

Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search

“…This makes BLMOL perform poorly for BL-MOPs which own an insufficient evaluation budget or a large UL search space. In the future, we plan to extend the BLMOL framework to more BL-MOPs in machine learning, such as feature selection [43], [44], federated learning [46], [84], and fair learning [85], [86]. In these paradigms, there often exist multiple objectives that need to be optimized simultaneously.…”