ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2403.06812
31
2

Monotone Individual Fairness

11 March 2024
Yahav Bechavod
ArXivPDFHTML
Abstract

We revisit the problem of online learning with individual fairness, where an online learner strives to maximize predictive accuracy while ensuring that similar individuals are treated similarly. We first extend the frameworks of Gillen et al. (2018); Bechavod et al. (2020), which rely on feedback from human auditors regarding fairness violations, as we consider auditing schemes that are capable of aggregating feedback from any number of auditors, using a rich class we term monotone aggregation functions. We then prove a characterization for such auditing schemes, practically reducing the analysis of auditing for individual fairness by multiple auditors to that of auditing by (instance-specific) single auditors. Using our generalized framework, we present an oracle-efficient algorithm achieving an upper bound frontier of (O(T1/2+2b),O(T3/4−b))(\mathcal{O}(T^{1/2+2b}),\mathcal{O}(T^{3/4-b}))(O(T1/2+2b),O(T3/4−b)) respectively for regret, number of fairness violations, for 0≤b≤1/40\leq b \leq 1/40≤b≤1/4. We then study an online classification setting where label feedback is available for positively-predicted individuals only, and present an oracle-efficient algorithm achieving an upper bound frontier of (O(T2/3+2b),O(T5/6−b))(\mathcal{O}(T^{2/3+2b}),\mathcal{O}(T^{5/6-b}))(O(T2/3+2b),O(T5/6−b)) for regret, number of fairness violations, for 0≤b≤1/60\leq b \leq 1/60≤b≤1/6. In both settings, our algorithms improve on the best known bounds for oracle-efficient algorithms. Furthermore, our algorithms offer significant improvements in computational efficiency, greatly reducing the number of required calls to an (offline) optimization oracle per round, to O~(α−2)\tilde{\mathcal{O}}(\alpha^{-2})O~(α−2) in the full information setting, and O~(α−2+k2T1/3)\tilde{\mathcal{O}}(\alpha^{-2} + k^2T^{1/3})O~(α−2+k2T1/3) in the partial information setting, where α\alphaα is the sensitivity for reporting fairness violations, and kkk is the number of individuals in a round.

View on arXiv
Comments on this paper