Graph Neural Networks Designed for Different Graph Types: A Survey

By Josephine M. Thomas et al

Published on March 10, 2023

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

Table of Contents

1 Introduction
2 Related Work
3 Foundations
3.1 Graphs And Their Properties
3.2 Static Structural Graph Properties
3.3 Dynamic Structural Graph Properties
4 Conclusion

Summary

This paper presents a survey on Graph Neural Networks (GNNs) designed for different graph types. The research field of GNNs has emerged to address cutting-edge problems based on graph data. The survey categorizes existing GNNs according to their ability to handle various graph types and properties. It provides an overview of structural, dynamic, and semantic properties of graphs. The paper covers the importance of GNN models for different graph types and properties, emphasizing the need for comprehensive models. The authors analyze existing GNN models and highlight gaps where certain graph types are not adequately covered. Overall, the survey aims to provide insights into the latest collection of GNNs and their categorization based on graph types and properties.