Flexibly Fair Representation Learning by Disentanglement

Elliot Creager
Elliot Creager
Jörn-Henrik Jacobsen
Jörn-Henrik Jacobsen
Marissa A. Weis
Marissa A. Weis

international conference on machine learning, 2019.

Cited by: 48|Bibtex|Views81
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and predictio...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments