Work

Renyi Fair Information Bottleneck for Image Classification

Year: 2022

Type: preprint

Abstract: 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 $α$ 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2203.04950

Authors: Gronowski, Adam, Paul, William, Alajaji, Fady, Gharesifard, Bahman, Burlina, Philippe

Institutions: Queen's University, Johns Hopkins University Applied Physics Laboratory, University of California, Los Angeles

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

SDG: Reduced inequalities

Open Access status: green

OpenAlex ID: W4226059660

Cites:

Cited by:

Related to: 10