Fairness Auditing with Multi-Agent Collaboration
This work addresses fairness auditing for platforms using ML models, but it is incremental as it builds on existing independent audit assumptions by introducing multi-agent collaboration.
The paper tackles the problem of fairness auditing by exploring multi-agent collaboration, finding that collaboration generally improves audit accuracy, basic sampling methods are effective, and excessive coordination can harm accuracy as agent numbers increase, with experiments on three large datasets confirming these results.
Existing work in fairness auditing assumes that each audit is performed independently. In this paper, we consider multiple agents working together, each auditing the same platform for different tasks. Agents have two levers: their collaboration strategy, with or without coordination beforehand, and their strategy for sampling appropriate data points. We theoretically compare the interplay of these levers. Our main findings are that (i) collaboration is generally beneficial for accurate audits, (ii) basic sampling methods often prove to be effective, and (iii) counter-intuitively, extensive coordination on queries often deteriorates audits accuracy as the number of agents increases. Experiments on three large datasets confirm our theoretical results. Our findings motivate collaboration during fairness audits of platforms that use ML models for decision-making.