CO*IR: A Greedy and Individually Fair Re-ranker

Research output: Contribution to journalConference articlepeer-review

Abstract

An open-source and greedy approach to individually fair re-ranking is presented, evaluated and tested. Previous literature on individually fair search suggested greedy-style heuristics, but no such designs or implementations were introduced before this writing. We release our re-ranker as a zero-dependency utility compatible with all major operating systems. We publish our re-ranker under a permissive software license (GPLv3). By explicitly considering individual fairness a post-processing (re-ranking) task, we implement the notion of individual fairness as a microservice, de-coupled from specific IR systems. Our software package works on commodity hardware, and finds application in small-to-medium-sized businesses, federated social networks, and under the broader open web search initiative.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume3744
Publication statusPublished - 2024
Externally publishedYes
Event1st Workshop on AI Bias: Measurements, Mitigation, Explanation Strategies, AIMMES 2024 - Amsterdam, Netherlands
Duration: 20 Mar 2024 → …

Keywords

  • fairness
  • individual fairness
  • open source
  • ranking

Fingerprint

Dive into the research topics of 'CO*IR: A Greedy and Individually Fair Re-ranker'. Together they form a unique fingerprint.

Cite this