# A Variational Information Bottleneck Approach to Multi-Omics Data Integration

arXiv: https://arxiv.org/abs/2102.03014 · HTML: https://mlsanity.com/paper/2102.03014/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 5 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions](https://mlsanity.com/paper/1410.7827/) (2014)
- [Structured Matrix Completion with Applications to Genomic Data Integration](https://mlsanity.com/paper/1504.01823/) (2015)
- [Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers](https://mlsanity.com/paper/1904.11151/) (2019)

## Built on by (most cited first, 30 of 40)

- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction](https://mlsanity.com/paper/2401.01646/) (2024)
- [On the Limitations of Multimodal VAEs](https://mlsanity.com/paper/2110.04121/) (2021)
- [Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Review](https://mlsanity.com/paper/2203.15588/) (2022)
- [Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning](https://mlsanity.com/paper/2404.09403/) (2024)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)
- [Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification](https://mlsanity.com/paper/2304.05165/) (2023)
- [Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses](https://mlsanity.com/paper/2310.03311/) (2023)
- [Evidential Deep Partial Multi-View Classification With Discount Fusion](https://mlsanity.com/paper/2408.13123/) (2024)
- [Multi-view Information Bottleneck Without Variational Approximation](https://mlsanity.com/paper/2204.10530/) (2022)
- [Interpretable Deep Learning Methods for Multiview Learning](https://mlsanity.com/paper/2302.07930/) (2023)
- [Treatment Outcome Prediction for Intracerebral Hemorrhage via Generative Prognostic Model with Imaging and Tabular Data](https://mlsanity.com/paper/2307.12858/) (2023)
- [Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives](https://mlsanity.com/paper/2309.00380/) (2023)
- [Disentanglement of Variations with Multimodal Generative Modeling](https://mlsanity.com/paper/2509.23548/) (2025)
- [CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning](https://mlsanity.com/paper/2602.04920/) (2026)
- [Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity](https://mlsanity.com/paper/2204.06242/) (2022)
- [Variational Distillation for Multi-View Learning](https://mlsanity.com/paper/2206.09548/) (2022)
- [Disentangling shared and private latent factors in multimodal Variational Autoencoders](https://mlsanity.com/paper/2403.06338/) (2024)
- [Discovering Common Information in Multi-view Data](https://mlsanity.com/paper/2406.15043/) (2024)
- [Robult: Leveraging Redundancy and Modality Specific Features for Robust Multimodal Learning](https://mlsanity.com/paper/2509.03477/) (2025)
- [CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data](https://mlsanity.com/paper/2304.05542/) (2023)
- [Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2408.16029/) (2024)
- [Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data](https://mlsanity.com/paper/2510.09513/) (2025)
- [Curriculum Learning Meets Weakly Supervised Modality Correlation Learning](https://mlsanity.com/paper/2212.07619/) (2022)
- [Integrate Any Omics: Towards genome-wide data integration for patient stratification](https://mlsanity.com/paper/2401.07937/) (2024)
- [Towards Robust Uncertainty-Aware Incomplete Multi-View Classification](https://mlsanity.com/paper/2409.06270/) (2024)
- [Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification](https://mlsanity.com/paper/2501.06524/) (2025)
- [Neuro-Inspired Hierarchical Multimodal Learning](https://mlsanity.com/paper/2309.15877/) (2023)
- [Self-supervised learning of multi-omics embeddings in the low-label, high-data regime](https://mlsanity.com/paper/2311.09962/) (2023)
- [Complementary Information Mutual Learning for Multimodality Medical Image Segmentation](https://mlsanity.com/paper/2401.02717/) (2024)

## Abstract (arXiv)

Integration of data from multiple omics techniques is becoming increasingly important in biomedical research. Due to non-uniformity and technical limitations in omics platforms, such integrative analyses on multiple omics, which we refer to as views, involve learning from incomplete observations with various view-missing patterns. This is challenging because i) complex interactions within and across observed views need to be properly addressed for optimal predictive power and ii) observations with various view-missing patterns need to be flexibly integrated. To address such challenges, we propose a deep variational information bottleneck (IB) approach for incomplete multi-view observations. Our method applies the IB framework on marginal and joint representations of the observed views to focus on intra-view and inter-view interactions that are relevant for the target. Most importantly, by modeling the joint representations as a product of marginal representations, we can efficiently learn from observed views with various view-missing patterns. Experiments on real-world datasets show that our method consistently achieves gain from data integration and outperforms state-of-the-art benchmarks.