Path-Specific Counterfactual Fairness

Authors

  • Silvia Chiappa DeepMind

DOI:

https://doi.org/10.1609/aaai.v33i01.33017801

Abstract

We consider the problem of learning fair decision systems from data in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a counterfactual approach to disregard effects along unfair pathways that does not incur in the same loss of individual-specific information as previous approaches. Our method corrects observations adversely affected by the sensitive attribute, and uses these to form a decision. We leverage recent developments in deep learning and approximate inference to develop a VAE-type method that is widely applicable to complex nonlinear models.

Downloads

Published

2019-07-17

How to Cite

Chiappa, S. (2019). Path-Specific Counterfactual Fairness. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7801-7808. https://doi.org/10.1609/aaai.v33i01.33017801

Issue

Section

AAAI Technical Track: Reasoning under Uncertainty