Renyi Fair Information Bottleneck for Image Classification
This addresses fairness in medical imaging classification, though it appears incremental as an adaptation of information bottleneck methods with Renyi divergence.
The paper tackled fairness in machine learning by developing the Renyi Fair Information Bottleneck method, which enforces demographic parity and equalized odds constraints for image classification on the EyePACS dataset, outperforming state-of-the-art techniques on metrics like accuracy gap and Rawls' minimal accuracy.
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.