Fairness in Generative Modeling: do it Unsupervised!

被引：1

作者：

Zameshina, M. ^{[1
,2
]}

Teytaud, O. ^{[2
]}

Teytaud, Fabien ^{[3
]}

Hosu, Vlad ^{[4
]}

Carraz, Nathanael ^{[5
]}

Najman, Laurent ^{[1
]}

Wagner, Markus ^{[6
]}

机构：

[1] Univ Gustave Eiffel, CNRS, ESIEE, LIGM, Paris, France

[2] Facebook AI Res, Paris, France

[3] Univ Littoral Cote dOpale, Dunkerque, France

[4] Univ Konstanz, Constance, Germany

[5] Univ Antananarivo, Antananarivo, Madagascar

[6] Univ Adelaide, Adelaide, SA, Australia

来源：

PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022 | 2022年

关键词：

Generative modeling; neural networks; fairness;

D O I：

10.1145/3520304.3528992

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling. More precisely, to design fair algorithms for as many sensitive variables as possible, including variables we might not be aware of, we assume no prior knowledge of sensitive variables: our algorithms use unsupervised fairness only, meaning no information related to the sensitive variables is used for our fairness-improving methods. All images of faces (even generated ones) have been removed to mitigate legal risks.

引用

页码：320 / 323

页数：4

共 50 条

[1] Modeling of Small Data with Unsupervised Generative Ensemble Learning
Dolgikh, Serge
5TH INTERNATIONAL CONFERENCE ON INFORMATICS & DATA-DRIVEN MEDICINE, IDDM 2022, 2022, 3302
[2] Unsupervised Generative Modeling Using Matrix Product States
Han, Zhao-Yu
Wang, Jun
Fan, Heng
Wang, Lei
Zhang, Pan
PHYSICAL REVIEW X, 2018, 8 (03):
[3] Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing
Borsoi, Ricardo Augusto
Imbiriba, Tales
Moreira Bermudez, Jose Carlos
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2020, 6 : 374 - 384
[4] Fairness in Unsupervised Learning
Deepak, P.
Jose, Joemon M.
Sanil, V
CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 3511 - 3512
[5] Unsupervised Primitive Discovery for Improved 3D Generative Modeling
Khan, Salman H.
Guo, Yulan
Hayat, Munawar
Barnes, Nick
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9731 - 9740
[6] On Measuring Fairness in Generative Models
Teo, Christopher T. H.
Abdollahzadeh, Milad
Cheung, Ngai-Man
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[7] Generative non-autoregressive unsupervised keyphrase extraction with neural topic modeling
Zhu, Xun
Lou, Yinxia
Zhao, Jing
Gao, Wang
Deng, Hongtao
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 120
[8] Generative Adversarial Phonology: Modeling Unsupervised Phonetic and Phonological Learning With Neural Networks
Begus, Gasper
FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2020, 3
[9] GENERATIVE MODELLING FOR UNSUPERVISED SCORE CALIBRATION
Bruemmer, Niko
Garcia-Romero, Daniel
2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[10] Unsupervised Neural Generative Semantic Hashing
Hansen, Casper
Hansen, Christian
Simonsen, Jakob Grue
Alstrup, Stephen
Lioma, Christina
PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19), 2019, : 735 - 744

← 1 2 3 4 5 →