Learning Deep Generative Models of Graphs

by   Yujia Li, et al.

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach for learning generative models over graphs, which can capture both their structure and attributes. Our approach uses graph neural networks to express probabilistic dependencies among a graph's nodes and edges, and can, in principle, learn distributions over any arbitrary graph. In a series of experiments our results show that once trained, our models can generate good quality samples of both synthetic graphs as well as real molecular graphs, both unconditionally and conditioned on data. Compared to baselines that do not use graph-structured representations, our models often perform far better. We also explore key challenges of learning generative models of graphs, such as how to handle symmetries and ordering of elements during the graph generation process, and offer possible solutions. Our work is the first and most general approach for learning generative models over arbitrary graphs, and opens new directions for moving away from restrictions of vector- and sequence-like knowledge representations, toward more expressive and flexible relational data structures.


page 1

page 2

page 3

page 4


A Systematic Survey on Deep Generative Models for Graph Generation

Graphs are important data representations for describing objects and the...

Towards quantitative methods to assess network generative models

Assessing generative models is not an easy task. Generative models shoul...

From Graph Generation to Graph Classification

This note describes a new approach to classifying graphs that leverages ...

Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing

We introduce the Contextual Graph Markov Model, an approach combining id...

Graph2Graph Learning with Conditional Autoregressive Models

We present a graph neural network model for solving graph-to-graph learn...

HiGeN: Hierarchical Multi-Resolution Graph Generative Networks

In real world domains, most graphs naturally exhibit a hierarchical stru...

Generalized Graph Pattern Matching

Most of the machine learning algorithms are limited to learn from flat d...

Please sign up or login with your details

Forgot password? Click here to reset