GraphRNN: A Deep Generative Model for Graphs

by   Jiaxuan You, et al.

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due to the non-unique, high-dimensional nature of graphs and the complex, non-local dependencies that exist between edges in a given graph. Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure. GraphRNN learns to generate graphs by training on a representative set of graphs and decomposes the graph generation process into a sequence of node and edge formations, conditioned on the graph structure generated so far. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.


page 1

page 2

page 3

page 4


GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation

Graph generative models have broad applications in biology, chemistry an...

CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation

Graph data structures are fundamental for studying connected entities. W...

Deep Generative Model for Sparse Graphs using Text-Based Learning with Augmentation in Generative Examination Networks

Graphs and networks are a key research tool for a variety of science fie...

Graph Embedding VAE: A Permutation Invariant Model of Graph Structure

Generative models of graph structure have applications in biology and so...

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Generating graph-structured data requires learning the underlying distri...

GraphGen-Redux: a Fast and Lightweight Recurrent Model for labeled Graph Generation

The problem of labeled graph generation is gaining attention in the Deep...

Edge-based sequential graph generation with recurrent neural networks

Graph generation with Machine Learning is an open problem with applicati...

Please sign up or login with your details

Forgot password? Click here to reset