Conference CORE A* ❝ 72 citations

Fairness by Learning Orthogonal Disentangled Representations

Hasan Sarhan, Nassir Navab, Abouzar Eslami, Shadi Albarqouni

16th European Conference on Computer Vision (ECCV), August 2020

Teaser figure

Abstract

Learning discriminative powerful representations is a crucial step for machine learning systems. Introducing invariance against arbitrary nuisance or sensitive attributes while performing well on specific tasks is an important problem in representation learning. This is mostly approached by purging the sensitive information from learned representations. In this paper, we propose a novel disentanglement approach to invariant representation problem. We disentangle the meaningful and sensitive representations by enforcing orthogonality constraints as a proxy for independence. We explicitly enforce the meaningful representation to be agnostic to sensitive information by entropy maximization. The proposed approach is evaluated on five publicly available datasets and compared with state of the art methods for learning fairness and invariance achieving the state of the art performance on three datasets and comparable performance on the rest. Further, we perform an ablative study to evaluate the effect of each component.

Interactive explainer

Auto-generated. This explainer was generated automatically with Claude (Anthropic) from the published paper. It simplifies the method and may contain errors — for a correct understanding, and for all results and numbers, please refer to the published paper (publisher version).

Research themes

Research areas

Funded by

Keywords

Deep LearningFairnessPowerful RepresentationComputer Vision

Lab authors

Cite (BibTeX)
@article{sarhan2020fairness,
 author = {Sarhan, Mhd Hasan and Navab, Nassir and Eslami, Abouzar and Albarqouni, Shadi},
 journal = {arXiv preprint arXiv:2003.05707},
 title = {Fairness by Learning Orthogonal Disentangled Representations},
 year = {2020}
}

Related publications