Graph2Graph Learning with Conditional Autoregressive Models

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.

References in corpus (9)

• Focal Loss for Dense Object Detection
• Variational Graph Auto-Encoders
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• TUDataset: A collection of benchmark datasets for learning with graphs
• Benchmarking Graph Neural Networks
• Multi-Objective Molecule Generation using Interpretable Substructures
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs