Graph Neural Networks: A Review of Methods and Applications

TL;DR

This paper reviews various graph neural network models, their design principles, applications across domains, and discusses open challenges for future research in graph-based learning.

Contribution

It provides a systematic categorization of GNN variants, a general design pipeline, and highlights open problems in the field.

Findings

GNN variants like GCN, GAT, and GRN have achieved state-of-the-art results.

The paper categorizes applications into multiple domains including physics, chemistry, biology, and NLP.

Identifies four open problems to guide future research in GNNs.

Abstract

Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.