Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

Yuge Shi, Siddharth N, Brooks Paige, Philip Torr

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Learning generative models that span multiple data modalities, such as vision and language, is often motivated by the desire to learn more useful, generalisable representations that faithfully capture common underlying factors between the modalities. In this work, we characterise successful learning of such models as the fulfilment of four criteria: i) implicit latent decomposition into shared and private subspaces, ii) coherent joint generation over all modalities, iii) coherent cross-generation across individual modalities, and iv) improved model learning for individual modalities through multi-modal integration. Here, we propose a mixture-of-experts multi-modal variational autoencoder (MMVAE) for learning of generative models on different sets of modalities, including a challenging image <-> language dataset, and demonstrate its ability to satisfy all four criteria, both qualitatively and quantitatively.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 32
EditorsH. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alché-Buc, E. Fox, R. Garnett
PublisherCurran Associates Inc
Number of pages12
Publication statusPublished - 8 Dec 2019
Event33rd Conference on Neural Information Processing Systems - Vancouver Convention Centre, Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019


Conference33rd Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2019
Internet address


Dive into the research topics of 'Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models'. Together they form a unique fingerprint.

Cite this