# Disentangled Variational Information Bottleneck for Multiview Representation Learning

arXiv: https://arxiv.org/abs/2105.07599 · HTML: https://mlsanity.com/paper/2105.07599/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 17 May 2021.

## Builds on (most cited first, 16 of 16)

- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [A Survey on Multi-view Learning](https://mlsanity.com/paper/1304.5634/) (2013)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [From ImageNet to Image Classification: Contextualizing Progress on Benchmarks](https://mlsanity.com/paper/2005.11295/) (2020)
- [Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle](https://mlsanity.com/paper/1802.09766/) (2018)
- [Gait Recognition via Disentangled Representation Learning](https://mlsanity.com/paper/1904.04925/) (2019)
- [Deep Variational Canonical Correlation Analysis](https://mlsanity.com/paper/1610.03454/) (2016)
- [Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis](https://mlsanity.com/paper/2001.03371/) (2020)

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

- [Graph Structure Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2112.08903/) (2021)
- [The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection](https://mlsanity.com/paper/2210.12384/) (2022)
- [Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering](https://mlsanity.com/paper/2209.06954/) (2022)
- [Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses](https://mlsanity.com/paper/2310.03311/) (2023)
- [Rethinking Multi-view Representation Learning via Distilled Disentangling](https://mlsanity.com/paper/2403.10897/) (2024)
- [Text Representation Distillation via Information Bottleneck Principle](https://mlsanity.com/paper/2311.05472/) (2023)
- [Disentangled Generation with Information Bottleneck for Few-Shot Learning](https://mlsanity.com/paper/2211.16185/) (2022)
- [Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification](https://mlsanity.com/paper/2601.05785/) (2026)

## Abstract (arXiv)

Multiview data contain information from multiple modalities and have potentials to provide more comprehensive features for diverse machine learning tasks. A fundamental question in multiview analysis is what is the additional information brought by additional views and can quantitatively identify this additional information. In this work, we try to tackle this challenge by decomposing the entangled multiview features into shared latent representations that are common across all views and private representations that are specific to each single view. We formulate this feature disentanglement in the framework of information bottleneck and propose disentangled variational information bottleneck (DVIB). DVIB explicitly defines the properties of shared and private representations using constrains from mutual information. By deriving variational upper and lower bounds of mutual information terms, representations are efficiently optimized. We demonstrate the shared and private representations learned by DVIB well preserve the common labels shared between two views and unique labels corresponding to each single view, respectively. DVIB also shows comparable performance in classification task on images with corruptions. DVIB implementation is available at https://github.com/feng-bao-ucsf/DVIB.