Using Protected Attributes to Consider Fairness in Multi-Agent Systems

TL;DR

This paper adapts fairness metrics from algorithmic fairness to multi-agent systems, enabling evaluation and design of systems that prevent disadvantage based on protected attributes.

Contribution

It introduces the use of demographic parity, counterfactual fairness, and conditional statistical parity metrics in MAS to assess and promote fairness.

Findings

Metrics successfully adapted to MAS context

Framework for evaluating fairness in multi-agent interactions

Potential for designing fairer multi-agent systems

Abstract

Fairness in Multi-Agent Systems (MAS) has been extensively studied, particularly in reward distribution among agents in scenarios such as goods allocation, resource division, lotteries, and bargaining systems. Fairness in MAS depends on various factors, including the system's governing rules, the behaviour of the agents, and their characteristics. Yet, fairness in human society often involves evaluating disparities between disadvantaged and privileged groups, guided by principles of Equality, Diversity, and Inclusion (EDI). Taking inspiration from the work on algorithmic fairness, which addresses bias in machine learning-based decision-making, we define protected attributes for MAS as characteristics that should not disadvantage an agent in terms of its expected rewards. We adapt fairness metrics from the algorithmic fairness literature -- namely, demographic parity, counterfactual fairness, and conditional statistical parity -- to the multi-agent setting, where self-interested agents interact within an environment. These metrics allow us to evaluate the fairness of MAS, with the ultimate aim of designing MAS that do not disadvantage agents based on protected attributes.