Renyi Fair Information Bottleneck for Image Classification

Autor:	Gronowski, Adam, Paul, William, Alajaji, Fady, Gharesifard, Bahman, Burlina, Philippe
Rok vydání:	2022
Předmět:	Computer Science - Machine Learning Computer Science - Information Theory
Druh dokumentu:	Working Paper
Popis:	We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB). We consider two different fairness constraints - demographic parity and equalized odds - for learning fair representations and derive a loss function via a variational approach that uses Renyi's divergence with its tunable parameter $\alpha$ and that takes into account the triple constraints of utility, fairness, and compactness of representation. We then evaluate the performance of our method for image classification using the EyePACS medical imaging dataset, showing it outperforms competing state of the art techniques with performance measured using a variety of compound utility/fairness metrics, including accuracy gap and Rawls' minimal accuracy. Comment: To appear in the Proceedings of CWIT'22
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.04950 Zobrazit plný text záznamu View this record from Arxiv