Learning Hierarchical Variational Autoencoders with Mutual Information Maximization for Autoregressive Sequence Modeling

Dong Qian*, William Kwok Wai Cheung

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

1 Citation (Scopus)


Variational autoencoders (VAEs) are a class of effective deep generative models, with the objective to approximate the true, but unknown data distribution. VAEs make use of latent variables to capture high-level semantics so as to reconstruct the data well with the help of informative latent variables. Yet, training VAEs tends to suffer from posterior collapse, when the decoder is parameterized by an autoregressive model for sequence generation. VAEs can be further enhanced by introducing multiple layers of latent variables, but the posterior collapse issue hinders the adoption of such hierarchical VAEs in real-world applications. In this paper, we introduce InfoMaxHVAE, which integrates mutual information estimated via neural networks into hierarchical VAEs to alleviate posterior collapse, when powerful autoregressive models are used for modeling sequences. Experimental results on a number of text and image datasets show that InfoMaxHVAE can outperform the state-of-the-art baselines and exhibits less posterior collapse. We further show that InfoMaxHVAE can shape a coarse-to-fine hierarchical organization of the latent space.

Original languageEnglish
Pages (from-to)1949-1962
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number2
Early online date21 Mar 2022
Publication statusPublished - 1 Feb 2023

Scopus Subject Areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics

User-Defined Keywords

  • Variational autoencoders (VAEs)
  • hierarchical variational autoencoders (HVAEs)
  • mutual information neural estimation
  • neural autoregressive sequence modeling


Dive into the research topics of 'Learning Hierarchical Variational Autoencoders with Mutual Information Maximization for Autoregressive Sequence Modeling'. Together they form a unique fingerprint.

Cite this