# Learning Interpretable Disentangled Representations using Adversarial VAEs

arXiv: https://arxiv.org/abs/1904.08491 · HTML: https://mlsanity.com/paper/1904.08491/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Label-Free Explainability for Unsupervised Models](https://mlsanity.com/paper/2203.01928/) (2022)
- [Deep Kernel Principal Component Analysis for Multi-level Feature Learning](https://mlsanity.com/paper/2302.11220/) (2023)
- [Seven challenges for harmonizing explainability requirements](https://mlsanity.com/paper/2108.05390/) (2021)
- [Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings](https://mlsanity.com/paper/2306.09035/) (2023)
- [Explainability and Robustness of Deep Visual Classification Models](https://mlsanity.com/paper/2301.01343/) (2023)
- [Representation learning from OCT images](https://mlsanity.com/paper/2605.02589/) (2026)

## Abstract (arXiv)

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact and explainable representation of the data. In this paper, we introduce a novel adversarial variational autoencoder with a total correlation constraint to enforce independence on the latent representation while preserving the reconstruction fidelity. Our proposed method is validated on a publicly available dataset showing that the learned disentangled representation is not only interpretable, but also superior to the state-of-the-art methods. We report a relative improvement of 81.50% in terms of disentanglement, 11.60% in clustering, and 2% in supervised classification with a few amounts of labeled data.