# Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis

arXiv: https://arxiv.org/abs/2106.13734 · HTML: https://mlsanity.com/paper/2106.13734/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 25 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Interpreting Deep Visual Representations via Network Dissection](https://mlsanity.com/paper/1711.05611/) (2017)
- [SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator](https://mlsanity.com/paper/1911.05856/) (2019)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)
- [Towards causal benchmarking of bias in face analysis algorithms](https://mlsanity.com/paper/2007.06570/) (2020)
- [Variational AutoEncoder For Regression: Application to Brain Aging Analysis](https://mlsanity.com/paper/1904.05948/) (2019)
- [Hierarchical VampPrior Variational Fair Auto-Encoder](https://mlsanity.com/paper/1806.09918/) (2018)

## Built on by (most cited first, 5 of 5)

- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models](https://mlsanity.com/paper/2207.04607/) (2022)
- [AI-based association analysis for medical imaging using latent-space geometric confounder correction](https://mlsanity.com/paper/2311.12836/) (2023)
- [Confounder-Free Continual Learning via Recursive Feature Normalization](https://mlsanity.com/paper/2507.09031/) (2025)
- [Controlling for Omitted Variable Bias in Deep Neural Networks](https://mlsanity.com/paper/2608.25930/) (2026)

## Abstract (arXiv)

Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by purging the bias information from learned representations. We however expect this strategy to harm the diversity of information in the representation, and thus limiting its prospective usage (e.g., interpretation). Therefore, we propose to mitigate the bias while keeping almost all information in the latent representations, which enables us to observe and interpret them as well. To achieve this, we project latent features onto a learned vector direction, and enforce the independence between biases and projected features rather than all learned features. To interpret the mapping between projected features and input data, we propose projection-wise disentangling: a sampling and reconstruction along the learned vector direction. The proposed method was evaluated on the analysis of 3D facial shape and patient characteristics (N=5011). Experiments showed that this conceptually simple method achieved state-of-the-art fair prediction performance and interpretability, showing its great potential for clinical applications.