Semi-Implicit Graph Variational Auto-Encoders

by   Arman Hasanzadeh, et al.

Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with a Bernoulli-Poisson link decoder. Not only does this hierarchical construction provide a more flexible generative graph model to better capture real-world graph properties, but also does SIG-VAE naturally lead to semi-implicit hierarchical variational inference that allows faithful modeling of implicit posteriors of given graph data, which may exhibit heavy tails, multiple modes, skewness, and rich dependency structures. Compared to VGAE, the derived graph latent representations by SIG-VAE are more interpretable, due to more expressive generative model and more faithful inference enabled by the flexible semi-implicit construction. Extensive experiments with a variety of graph data show that SIG-VAE significantly outperforms state-of-the-art methods on several different graph analytic tasks.


page 1

page 2

page 3

page 4


Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference

Efficient modeling of relational data arising in physical, social, and i...

Hierarchical Representations with Poincaré Variational Auto-Encoders

The Variational Auto-Encoder (VAE) model has become widely popular as a ...

Nonparametric Topic Modeling with Neural Inference

This work focuses on combining nonparametric topic models with Auto-Enco...

Variational framework for partially-measured physical system control: examples of vision neuroscience and optical random media

To characterize a physical system to behave as desired, either its under...

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Recent work on generative modeling of text has found that variational au...

Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization

Personalization of cardiac models involves the optimization of organ tis...

Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion

Models of human motion commonly focus either on trajectory prediction or...