References & Citations
Computer Science > Machine Learning
Title: Fairness Auditing with Multi-Agent Collaboration
(Submitted on 13 Feb 2024 (this version), latest version 26 Apr 2024 (v2))
Abstract: Existing work in fairness audits assumes that agents operate independently. In this paper, we consider the case of multiple agents auditing the same platform for different tasks. Agents have two levers: their collaboration strategy, with or without coordination beforehand, and their sampling method. We theoretically study their interplay when agents operate independently or collaborate. We prove that, surprisingly, coordination can sometimes be detrimental to audit accuracy, whereas uncoordinated collaboration generally yields good results. Experimentation on real-world datasets confirms this observation, as the audit accuracy of uncoordinated collaboration matches that of collaborative optimal sampling.
Submission history
From: Jade Garcia Bourrée [view email][v1] Tue, 13 Feb 2024 15:24:46 GMT (521kb,D)
[v2] Fri, 26 Apr 2024 13:44:32 GMT (446kb,D)
Link back to: arXiv, form interface, contact.