An efficient discrimination discovery method for fairness testing

Shinya Sano, Takashi Kitamura, Shingo Takada

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルSEKE 2022 - Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering
出版社Knowledge Systems Institute Graduate School
ページ200-205
ページ数6
ISBN(電子版)1891706543, 9781891706547
DOI
出版ステータスPublished - 2022
イベント34th International Conference on Software Engineering and Knowledge Engineering, SEKE 2022 - Pittsburgh, United States
継続期間: 2022 7月 12022 7月 10

出版物シリーズ

名前Proceedings of the International Conference on Software Engineering and Knowledge Engineering, SEKE
ISSN(印刷版)2325-9000
ISSN(電子版)2325-9086

Conference

Conference34th International Conference on Software Engineering and Knowledge Engineering, SEKE 2022
国/地域United States
CityPittsburgh
Period22/7/122/7/10

ASJC Scopus subject areas

  • ソフトウェア

フィンガープリント

「An efficient discrimination discovery method for fairness testing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル