An efficient discrimination discovery method for fairness testing

Shinya Sano, Takashi Kitamura, Shingo Takada

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With the increasing use of machine learning software in our daily life, software fairness has become a growing concern. In this paper, we propose an individual fairness testing technique called KOSEI. Individual fairness is one of the central concepts in software fairness. Testing individual fairness aims to detect individual discriminations included in the software. KOSEI is based on AEQUITAS by Udeshi et al., a landmark fairness testing technique featuring a two-step search strategy of global and local search. KOSEI improves the local search part of AEQUITAS, based on our insight to overcome the limitations of the local search of AEQUITAS. Our experiments show that KOSEI outperforms AEQUITAS by orders of magnitude. KOSEI, on average, detects 5,084.8% more discriminations than AEQUITAS, in just 7.5% of the execution time.

Original languageEnglish
Title of host publicationSEKE 2022 - Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering
PublisherKnowledge Systems Institute Graduate School
Pages200-205
Number of pages6
ISBN (Electronic)1891706543, 9781891706547
DOIs
Publication statusPublished - 2022
Event34th International Conference on Software Engineering and Knowledge Engineering, SEKE 2022 - Pittsburgh, United States
Duration: 2022 Jul 12022 Jul 10

Publication series

NameProceedings of the International Conference on Software Engineering and Knowledge Engineering, SEKE
ISSN (Print)2325-9000
ISSN (Electronic)2325-9086

Conference

Conference34th International Conference on Software Engineering and Knowledge Engineering, SEKE 2022
Country/TerritoryUnited States
CityPittsburgh
Period22/7/122/7/10

Keywords

  • algorithm fairness
  • machine learning
  • software testing

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'An efficient discrimination discovery method for fairness testing'. Together they form a unique fingerprint.

Cite this