Disentangling shared and private latent factors in multimodal variational autoencoders

Conference item

Generative models for multimodal data permit the identification of latent factors that may be associated with important determinants of observed data heterogeneity. Common or shared factors could be important for explaining variation across modalities whereas other factors may be private and important only for the explanation of a single modality. Multimodal Variational Autoencoders, such as MVAE and MMVAE, are a natural choice for inferring those underlying latent factors and separating shared variation from private. In this work, we investigate their capability to reliably perform this disentanglement. In particular, we highlight a challenging problem setting where modality-specific variation dominates the shared signal. Taking a cross-modal prediction perspective, we demonstrate limitations of existing models, and propose a modification how to make them more robust to modality-specific variation. Our findings are supported by experiments on synthetic as well as various real-world multi-omics data sets.

Authors: Märtens, K; Yau, C

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: PMLR
• Host title: Proceedings of the 18th Machine Learning in Computational Biology meeting
• Pages: 60-75
• Series: Proceedings of Machine Learning Research
• Series number: 240
• Publication date: 2024-03-15
• Acceptance date: 2023-11-02
• Event title: 18th Machine Learning in Computational Biology (MLCB 2023)
• Event location: Seattle, WA, USA
• Event website: https://sites.google.com/cs.washington.edu/mlcb2023/
• Event start date: 2023-11-30
• Event end date: 2023-12-01
• EISSN: 2640-3498
• ISSN: 2640-3498
• Language: English