A systematic analysis and guidelines of graph neural networks for practical applications

Jin Young Kim, Sung Bae Cho

Research output: Contribution to journalArticlepeer-review

Abstract

A graph neural network (GNN) draws attention to deal with many problems in social networks and bioinformatics, as graph data proliferate in a wide variety of applications. Despite the large amount of investigation, it is still difficult to choose the most suitable method for a given problem due to the lack of a thorough analysis on the feasible methods. An anatomical comparison of GNNs would help to devise a prospective method for better solution to real-world problems. In order to give guidelines to make full use of the GNN for graph classification, this paper attempts to analyze the state-of-the-art methods of the GNN and provide practicable guidelines for applications. The representative methods are described with a systematic scheme in four phases for GNN: 1) pre-processing, 2) aggregation, 3) readout, and 4) classification with graph embedding, resulting in a large coverage of more than 1300 methods. The 13 well-known benchmark datasets are categorized into three types with respect to the properties of graph data such as connectivity. In total, more than 3600 runs are executed to systematically analyze and compare the GNN models while changing only one method for each phase. Experimental reproducibility and replicability are also verified by comparing the results with the performance from the literature. Finally, five guidelines for an appropriate model are deduced according to the graph characteristics such as complexity on connectivity and node feature.

Original languageEnglish
Article number115466
JournalExpert Systems with Applications
Volume184
DOIs
Publication statusPublished - 2021 Dec 1

Bibliographical note

Funding Information:
The authors thank Tae-Yong Kong and Hyung-Joon Moon for their help to prepare for the manuscripts. This work was partially supported by an IITP grant funded by the Korean government ( MSIT ) (No. 2020-0-01361 , Artificial Intelligence Graduate School Program ( Yonsei University )) and Electronics and Telecommunications Research Institute ( ETRI ) grant funded by the Korean government ( 21ZS1100 , Core Technology Research for Self-Improving Integrated Artificial Intelligence System).

Publisher Copyright:
© 2021

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A systematic analysis and guidelines of graph neural networks for practical applications'. Together they form a unique fingerprint.

Cite this