DeepAI AI Chat
Log In Sign Up

Adversarial Stein Training for Graph Energy Models

by   Shiv Shankar, et al.
University of Massachusetts Amherst

Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. Unlike standard EBM training methods our approach is to learn the model via minimizing adversarial stein discrepancy. Samples from the model can be obtained via Langevin dynamics based MCMC. We find that this approach achieves competitive results on graph generation compared to benchmark models.


page 1

page 2

page 3

page 4


Permutation Invariant Graph Generation via Score-Based Generative Modeling

Learning generative models for graph-structured data is challenging beca...

Scalable Graph Neural Networks for Heterogeneous Graphs

Graph neural networks (GNNs) are a popular class of parametric model for...

Training Graph Neural Networks by Graphon Estimation

In this work, we propose to train a graph neural network via resampling ...

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Learning on graphs, where instance nodes are inter-connected, has become...

Graph Normalizing Flows

We introduce graph normalizing flows: a new, reversible graph neural net...

Universal Invariant and Equivariant Graph Neural Networks

Graph Neural Networks (GNN) come in many flavors, but should always be e...

Graph Neural Network Based Node Deployment for Throughput Enhancement

The recent rapid growth in mobile data traffic entails a pressing demand...