Procedural Fairness in Multi-Agent Bandits

2026-01-15

AI Summary

This study addresses a critical gap in traditional multi-agent multi-armed bandit research, which has predominantly emphasized outcome fairness—such as utility equity or welfare maximization—while neglecting procedural justice and equal voice in decision-making. For the first time, the paper introduces procedural fairness into the multi-agent bandwidth allocation problem by integrating the multi-armed bandit framework with cooperative game theory’s core concept and principles of proportional representation. The proposed mechanism jointly ensures decisional equality and proportional outcomes. Theoretical analysis reveals fundamental value conflicts among different fairness criteria, underscoring that fairness must be grounded in explicit normative foundations. Experimental results demonstrate that the approach significantly enhances agents’ decisional representativeness and participatory rights with negligible sacrifice to outcome fairness, whether measured by egalitarian or utilitarian metrics.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Fair Division
• Machine Learning: Online Learning & Bandits

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or balancing utilities. However, evidence in psychology, economics, and Rawlsian theory suggests that fairness is also about process and who gets a say in the decisions being made. We introduce a new fairness objective, procedural fairness, which provides equal decision-making power for all agents, lies in the core, and provides for proportionality in outcomes. Empirical results confirm that fairness notions based on optimizing for outcomes sacrifice equal voice and representation, while the sacrifice in outcome-based fairness objectives (like equality and utilitarianism) is minimal under procedurally fair policies. We further prove that different fairness notions prioritize fundamentally different and incompatible values, highlighting that fairness requires explicit normative choices. This paper argues that procedural legitimacy deserves greater focus as a fairness objective, and provides a framework for putting procedural fairness into practice.

Problem

• procedural fairness
• multi-agent bandits
• decision-making power
• fairness in AI
• normative choices

Innovation

• procedural fairness
• multi-agent multi-armed bandits
• core stability
• equal decision-making power
• fairness trade-offs