Bias analysis and mitigation in data-driven tools using provenance

Yuval Moskovitch; Jinyang Li; H. V. Jagadish

doi:10.1145/3530800.3534528

Bias analysis and mitigation in data-driven tools using provenance

Yuval Moskovitch, Jinyang Li, H. V. Jagadish

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

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 language	English
Title of host publication	Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022
Publisher	Association for Computing Machinery, Inc
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781450393492
DOIs	https://doi.org/10.1145/3530800.3534528
State	Published - 17 Jun 2022
Externally published	Yes
Event	14th 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

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

Conference

Conference	14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022
Country/Territory	United States
City	Philadelphia
Period	17/06/22 → …

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1145/3530800.3534528

Cite this

Moskovitch, Y., Li, J., & Jagadish, H. V. (2022). Bias analysis and mitigation in data-driven tools using provenance. In Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022 (pp. 1-4). (Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022). Association for Computing Machinery, Inc. https://doi.org/10.1145/3530800.3534528

@inproceedings{64fa19b6ee5e4fabbf967a5a091a157c,

title = "Bias analysis and mitigation in data-driven tools using provenance",

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.",

author = "Yuval Moskovitch and Jinyang Li and Jagadish, {H. V.}",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022 ; Conference date: 17-06-2022",

year = "2022",

month = jun,

day = "17",

doi = "10.1145/3530800.3534528",

language = "English",

series = "Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022",

publisher = "Association for Computing Machinery, Inc",

pages = "1--4",

booktitle = "Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022",

}

Moskovitch, Y, Li, J & Jagadish, HV 2022, Bias analysis and mitigation in data-driven tools using provenance. in Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022. Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, Association for Computing Machinery, Inc, pp. 1-4, 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022, Philadelphia, United States, 17/06/22. https://doi.org/10.1145/3530800.3534528

Bias analysis and mitigation in data-driven tools using provenance. / Moskovitch, Yuval; Li, Jinyang; Jagadish, H. V.
Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022. Association for Computing Machinery, Inc, 2022. p. 1-4 (Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Bias analysis and mitigation in data-driven tools using provenance

AU - Moskovitch, Yuval

AU - Li, Jinyang

AU - Jagadish, H. V.

PY - 2022/6/17

Y1 - 2022/6/17

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85133759402&partnerID=8YFLogxK

U2 - 10.1145/3530800.3534528

DO - 10.1145/3530800.3534528

M3 - Conference contribution

AN - SCOPUS:85133759402

T3 - Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022

SP - 1

EP - 4

BT - Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022

PB - Association for Computing Machinery, Inc

T2 - 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022, held in conjunction with SIGMOD 2022

Y2 - 17 June 2022

ER -

Moskovitch Y, Li J, Jagadish HV. Bias analysis and mitigation in data-driven tools using provenance. In Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022. Association for Computing Machinery, Inc. 2022. p. 1-4. (Proceedings of 14th International Workshop on the Theory and Practice of Provenance, TaPP 2022). doi: 10.1145/3530800.3534528

Bias analysis and mitigation in data-driven tools using provenance

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this