3708.pdf (541.83 kB)
Discovering fair representations in the data domain
conference contribution
posted on 2023-06-09, 17:31 authored by Novi QuadriantoNovi Quadrianto, Viktoriia SharmanskaViktoriia Sharmanska, Oliver ThomasInterpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may include photographs. One promising direction to achieve fairness is by learning data representations that remove the semantics of protected characteristics, and are therefore able to mitigate unfair outcomes. All available models however learn latent embeddings which comes at the cost of being uninterpretable. We propose to cast this problem as data-to-data translation, i.e. learning a mapping from an input domain to a fair target domain, where a fairness definition is being enforced. Here the data domain can be images, or any tabular data representation. This task would be straightforward if we had fair target data available, but this is not the case. To overcome this, we learn a highly unconstrained mapping by exploiting statistics of residuals -- the difference between input data and its translated version -- and the protected characteristics. When applied to the CelebA dataset of face images with gender attribute as the protected characteristic, our model enforces equality of opportunity by adjusting the eyes and lips regions. Intriguingly, on the same dataset we arrive at similar conclusions when using semantic attribute representations of images for translation. On face images of the recent DiF dataset, with the same gender attribute, our method adjusts nose regions. In the Adult income dataset, also with protected gender attribute, our model achieves equality of opportunity by, among others, obfuscating the wife and husband relationship. Analyzing those systematic changes will allow us to scrutinize the interplay of fairness criterion, chosen protected characteristics, and prediction performance.
Funding
EthicalML: Injecting Ethical and Legal Constraints into Machine Learning Models; G2034; EPSRC-ENGINEERING & PHYSICAL SCIENCES RESEARCH COUNCIL
History
Publication status
- Published
File Version
- Accepted version
Journal
Conference on Computer Vision and Pattern Recognition (CVPR)ISSN
2575-7075Publisher
Institute of Electrical and Electronics EngineersExternal DOI
Volume
1Page range
8219-8228Event name
CVPR 2019Event location
Long Beach, California, USEvent type
conferenceEvent date
June 15th - June 20th 2019Place of publication
Los Alamitos, CAISBN
9781728132938Department affiliated with
- Informatics Publications
Research groups affiliated with
- Data Science Research Group Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2019-04-08First Open Access (FOA) Date
2019-04-08First Compliant Deposit (FCD) Date
2019-04-08Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC