# Renyi Fair Information Bottleneck for Image Classification

arXiv: https://arxiv.org/abs/2203.04950 · HTML: https://mlsanity.com/paper/2203.04950/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [R'enyi Divergence Variational Inference](https://mlsanity.com/paper/1602.02311/) (2016)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [Diversity in Faces](https://mlsanity.com/paper/1901.10436/) (2019)
- [The Conditional Entropy Bottleneck](https://mlsanity.com/paper/2002.05379/) (2020)
- [Nonlinear Information Bottleneck](https://mlsanity.com/paper/1705.02436/) (2017)
- [Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets](https://mlsanity.com/paper/1910.13268/) (2019)
- [Fairness in Supervised Learning: An Information Theoretic Approach](https://mlsanity.com/paper/1801.04378/) (2018)
- [A Variational Approach to Privacy and Fairness](https://mlsanity.com/paper/2006.06332/) (2020)
- [TARA: Training and Representation Alteration for AI Fairness and Domain Generalization](https://mlsanity.com/paper/2012.06387/) (2020)
- [Realizing GANs via a Tunable Loss Function](https://mlsanity.com/paper/2106.05232/) (2021)
- [Cumulant GAN](https://mlsanity.com/paper/2006.06625/) (2020)
- [Least kth-Order and R'enyi Generative Adversarial Networks](https://mlsanity.com/paper/2006.02479/) (2020)

## Built on by (most cited first, 3 of 3)

- [Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Review](https://mlsanity.com/paper/2209.13177/) (2022)
- [A survey of recent methods for addressing AI fairness and bias in biomedicine](https://mlsanity.com/paper/2402.08250/) (2024)
- [Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measures](https://mlsanity.com/paper/2206.10043/) (2022)

## Abstract (arXiv)

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.