Graph2Graph Learning with Conditional Autoregressive Models

TL;DR

This paper introduces a graph neural network model designed for graph-to-graph learning tasks, capable of handling complex graph-structured outputs and demonstrating its effectiveness through various challenging experiments.

Contribution

It presents a novel conditional autoregressive model for graph-to-graph learning, expanding the capabilities of graph neural networks beyond simple classification tasks.

Findings

Effective in subgraph prediction tasks

Useful as a graph autoencoder for reconstruction

Pretraining representations improves graph classification with limited labels

Abstract

We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers ``simple'' problems such as graph classification or regressing real-valued graph properties. For such tasks, the main requirement for intermediate representations of the data is to maintain the structure needed for output, i.e., keeping classes separated or maintaining the order indicated by the regressor. However, a number of learning tasks, such as regressing graph-valued output, generative models, or graph autoencoders, aim to predict a graph-structured output. In order to successfully do this, the learned representations need to preserve far more structure. We present a conditional auto-regressive model for graph-to-graph learning and illustrate its representational capabilities via experiments on challenging subgraph predictions from graph algorithmics; as a graph autoencoder for reconstruction and visualization; and on pretraining representations that allow graph classification with limited labeled data.