TY - GEN
T1 - An efficient discrimination discovery method for fairness testing
AU - Sano, Shinya
AU - Kitamura, Takashi
AU - Takada, Shingo
N1 - Funding Information:
This paper is based on results obtained from a project, JPNP20006, commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
Publisher Copyright:
© 2022 Knowledge Systems Institute Graduate School. All rights reserved.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - algorithm fairness
KW - machine learning
KW - software testing
UR - http://www.scopus.com/inward/record.url?scp=85137169398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137169398&partnerID=8YFLogxK
U2 - 10.18293/SEKE2022-064
DO - 10.18293/SEKE2022-064
M3 - Conference contribution
AN - SCOPUS:85137169398
T3 - Proceedings of the International Conference on Software Engineering and Knowledge Engineering, SEKE
SP - 200
EP - 205
BT - SEKE 2022 - Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering
PB - Knowledge Systems Institute Graduate School
T2 - 34th International Conference on Software Engineering and Knowledge Engineering, SEKE 2022
Y2 - 1 July 2022 through 10 July 2022
ER -