Bias analysis and mitigation in data-driven tools using provenance

Yuval Moskovitch, Jinyang Li, H. V. Jagadish

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Fairness and bias mitigation in data-driven systems has been extensively studied in recent years. In this paper, we suggest a novel approach towards fairness analysis and bias mitigation utilizing the notion of provenance, which was shown to be useful for similar tasks in the context of data and process analyses. We illustrate the idea using a simple use-case demonstrating a scenario of mitigating bias caused by inadequate minority group representation. We conclude with an outline of opportunities and challenges in developing provenance-based solutions for bias analysis and mitigation in data-driven systems.

Original languageEnglish
Title of host publicationProceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022
PublisherAssociation for Computing Machinery, Inc
Pages1-4
Number of pages4
ISBN (Electronic)9781450393492
DOIs
StatePublished - 17 Jun 2022
Externally publishedYes
Event14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022 - Philadelphia, United States
Duration: 17 Jun 2022 → …

Publication series

NameProceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022

Conference

Conference14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022
Country/TerritoryUnited States
CityPhiladelphia
Period17/06/22 → …

ASJC Scopus subject areas

  • Computer Science (all)

Cite this