Graph Neural Networks: A Review of Methods and Applications

By J. Zhou et al.

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. General design pipeline of GNNs
3. Propagation Module
4. Sampling Module
5. Pooling Module
6. Existing Variants and Applications
7. Open Problems and Future Research

Summary

This paper provides a thorough review of different graph neural network models as well as a systematic taxonomy of the applications. The authors propose a general design pipeline for GNN models and discuss the variants of each component. The paper categorizes the applications into structural and non-structural scenarios, presenting major applications and methods for each scenario. Additionally, four open problems for future research are proposed. The architecture of the GNN model includes propagation, sampling, and pooling modules, stacked to obtain better representations. Overall, the paper aims to contribute to the advancement of graph neural networks in various domains.