English

SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks

Machine Learning 2022-04-27 v1 Machine Learning

Abstract

Initial work on variational autoencoders assumed independent latent variables with simple distributions. Subsequent work has explored incorporating more complex distributions and dependency structures: including normalizing flows in the encoder network allows latent variables to entangle non-linearly, creating a richer class of distributions for the approximate posterior, and stacking layers of latent variables allows more complex priors to be specified for the generative model. This work explores incorporating arbitrary dependency structures, as specified by Bayesian networks, into VAEs. This is achieved by extending both the prior and inference network with graphical residual flows - residual flows that encode conditional independence by masking the weight matrices of the flow's residual blocks. We compare our model's performance on several synthetic datasets and show its potential in data-sparse settings.

Keywords

Cite

@article{arxiv.2204.11847,
  title  = {SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks},
  author = {Jacobie Mouton and Steve Kroon},
  journal= {arXiv preprint arXiv:2204.11847},
  year   = {2022}
}

Comments

To appear in ICLR 2022 workshop Deep Generative Models for Highly Structured Data

R2 v1 2026-06-24T10:58:08.619Z