講演名 | 2022-03-09 Fairness Testing of Machine Learning Software through a Combinatorial Approach Daniel Perez Morales(AIST and Keio Univ.), Takashi Kitamura(AIST), Shingo Takada(Keio Univ.), |
---|---|
PDFダウンロードページ | PDFダウンロードページへ |
抄録(和) | Machine learning (ML) can be used in decision-making algorithms or classifiers. These classifiers must be tested looking for discrimination. It is an unintended behavior and can disfavor certain individuals based on their protected attributes, such as race or gender. Aequitas, a well-known black-box technique for fairness testing, tests ML software to find discrimination. Although Aequitas has several technical advantages, it largely relies on random sampling. We propose Coverage-Guided Fairness Testing (CGFT). CGFT applies combinatorial t-way testing when searching for discriminatory data. We evaluate CGFT with Aequitas, showing an improvement in the number of discrimination found using CGFT. |
抄録(英) | Machine learning (ML) can be used in decision-making algorithms or classifiers. These classifiers must be tested looking for discrimination. It is an unintended behavior and can disfavor certain individuals based on their protected attributes, such as race or gender. Aequitas, a well-known black-box technique for fairness testing, tests ML software to find discrimination. Although Aequitas has several technical advantages, it largely relies on random sampling. We propose Coverage-Guided Fairness Testing (CGFT). CGFT applies combinatorial t-way testing when searching for discriminatory data. We evaluate CGFT with Aequitas, showing an improvement in the number of discrimination found using CGFT. |
キーワード(和) | Fairness testing / Combinatorial testing / Machine learning |
キーワード(英) | Fairness testing / Combinatorial testing / Machine learning |
資料番号 | KBSE2021-50 |
発行日 | 2022-03-02 (KBSE) |
研究会情報 | |
研究会 | KBSE |
---|---|
開催期間 | 2022/3/9(から2日開催) |
開催地(和) | オンライン開催(Zoom) |
開催地(英) | Online |
テーマ(和) | 一般,学生 |
テーマ(英) | General, Student |
委員長氏名(和) | 中川 博之(阪大) |
委員長氏名(英) | Hiroyuki Nakagawa(Osaka Univ.) |
副委員長氏名(和) | 猿渡 卓也(NTTデータ) |
副委員長氏名(英) | Takuya Saruwatari(NTT Data) |
幹事氏名(和) | 小形 真平(信州大) / 槇原 絵里奈(同志社大) |
幹事氏名(英) | Shinpei Ogata(Shinshu Univ) / Erina Nakihara(Doshisha Univ,) |
幹事補佐氏名(和) | 小島 英春(阪大) / 柏 祐太郎(九大) |
幹事補佐氏名(英) | Hideharu Kojima(Osaka Univ.) / Yutaro Kashiwa(Kyushu Univ,) |
講演論文情報詳細 | |
申込み研究会 | Technical Committee on Knowledge-Based Software Engineering |
---|---|
本文の言語 | ENG |
タイトル(和) | |
サブタイトル(和) | |
タイトル(英) | Fairness Testing of Machine Learning Software through a Combinatorial Approach |
サブタイトル(和) | |
キーワード(1)(和/英) | Fairness testing / Fairness testing |
キーワード(2)(和/英) | Combinatorial testing / Combinatorial testing |
キーワード(3)(和/英) | Machine learning / Machine learning |
第 1 著者 氏名(和/英) | Daniel Perez Morales / Daniel Perez Morales |
第 1 著者 所属(和/英) | National Institute of Advanced Industrial Science and Keio Univ.(略称:AIST and Keio Univ.) National Institute of Advanced Industrial Science and Keio Univ.(略称:AIST and Keio Univ.) |
第 2 著者 氏名(和/英) | Takashi Kitamura / Takashi Kitamura |
第 2 著者 所属(和/英) | National Institute of Advanced Industrial Science(略称:AIST) National Institute of Advanced Industrial Science(略称:AIST) |
第 3 著者 氏名(和/英) | Shingo Takada / Shingo Takada |
第 3 著者 所属(和/英) | Keio University(略称:Keio Univ.) Keio University(略称:Keio Univ.) |
発表年月日 | 2022-03-09 |
資料番号 | KBSE2021-50 |
巻番号(vol) | vol.121 |
号番号(no) | KBSE-424 |
ページ範囲 | pp.54-59(KBSE), |
ページ数 | 6 |
発行日 | 2022-03-02 (KBSE) |