# Learning Disentangled Representations via Mutual Information Estimation

arXiv: https://arxiv.org/abs/1912.03915 · HTML: https://mlsanity.com/paper/1912.03915/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2019.

## Built on by (most cited first, 30 of 52)

- [EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations](https://mlsanity.com/paper/2207.06635/) (2022)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Disentangling Hate in Online Memes](https://mlsanity.com/paper/2108.06207/) (2021)
- [Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction](https://mlsanity.com/paper/2401.01646/) (2024)
- [Multimodal Variational Auto-encoder based Audio-Visual Segmentation](https://mlsanity.com/paper/2310.08303/) (2023)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [Specificity-Preserving Federated Learning for MR Image Reconstruction](https://mlsanity.com/paper/2112.05752/) (2021)
- [Generalizing Graph ODE for Learning Complex System Dynamics across Environments](https://mlsanity.com/paper/2307.04287/) (2023)
- [DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies](https://mlsanity.com/paper/2301.08164/) (2023)
- [Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection](https://mlsanity.com/paper/2401.10731/) (2024)
- [An Information Criterion for Controlled Disentanglement of Multimodal Data](https://mlsanity.com/paper/2410.23996/) (2024)
- [Improving Adversarial Robustness via Mutual Information Estimation](https://mlsanity.com/paper/2207.12203/) (2022)
- [Gacs-Korner Common Information Variational Autoencoder](https://mlsanity.com/paper/2205.12239/) (2022)
- [STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification](https://mlsanity.com/paper/2503.06277/) (2025)
- [DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2503.22912/) (2025)
- [CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts](https://mlsanity.com/paper/2311.16445/) (2023)
- [Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers](https://mlsanity.com/paper/2405.16419/) (2024)
- [DRIM: Learning Disentangled Representations from Incomplete Multimodal Healthcare Data](https://mlsanity.com/paper/2409.17055/) (2024)
- [Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition](https://mlsanity.com/paper/2202.07260/) (2022)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Supervised structure learning](https://mlsanity.com/paper/2311.10300/) (2023)
- [Content-Context Factorized Representations for Automated Speech Recognition](https://mlsanity.com/paper/2205.09872/) (2022)
- [Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization](https://mlsanity.com/paper/2103.13125/) (2021)
- [On the relationship between disentanglement and multi-task learning](https://mlsanity.com/paper/2110.03498/) (2021)
- [Active Inference and Intentional Behaviour](https://mlsanity.com/paper/2312.07547/) (2023)
- [Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision](https://mlsanity.com/paper/2103.03240/) (2021)
- [Disentanglement by Cyclic Reconstruction](https://mlsanity.com/paper/2112.12980/) (2021)
- [Disentangled Representation Learning with Transmitted Information Bottleneck](https://mlsanity.com/paper/2311.01686/) (2023)
- [Constrained Multiview Representation for Self-supervised Contrastive Learning](https://mlsanity.com/paper/2402.03456/) (2024)
- [Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense](https://mlsanity.com/paper/2402.18787/) (2024)

## Abstract (arXiv)

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation that captures the common information between the images and an exclusive representation that contains the specific information of each image. To address this issue, we propose a model based on mutual information estimation without relying on image reconstruction or image generation. Mutual information maximization is performed to capture the attributes of data in the shared and exclusive representations while we minimize the mutual information between the shared and exclusive representation to enforce representation disentanglement. We show that these representations are useful to perform downstream tasks such as image classification and image retrieval based on the shared or exclusive component. Moreover, classification results show that our model outperforms the state-of-the-art model based on VAE/GAN approaches in representation disentanglement.