Determining the Optimal Number of GAT and GCN Layers for Node Classification in Graph Neural Networks

Humaira Noor, Niful Islam, Md Saddam Hossain Mukta, Nur Shazwani Binti Kamarudin, Mohaimenul Azam Khan Raiaan, Sami Azam

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in Proceedingspeer-review

Abstract

Node classification in complex networks plays an important role including social network analysis and recommendation systems. Some graph neural networks such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) have emerged as effective approaches for achieving high-performance classification in such tasks. However, constructing a graph neural network architecture is challenging particularly due to the complex task of determining the optimal number of layers. This study presents a mathematical formula for determining the optimal number of GCN and GAT hidden layers. The experiment was conducted on ten benchmark datasets, evaluating performance metrices such as accuracy, precision, recall, F1-score, and MCC for identifying the best estimation of number of hidden layers. According to the experimental findings, the number of GAT and GCN layers selected has a substantial impact on classification accuracy. Studies show that adding extra layers after the optimum number of layers has a negative or no impact on the classification performance. Our proposed approximation technique may provide valuable insights for enhancing efficiency and accuracy of the Graph Neural Network algorithms.

Original languageEnglish
Title of host publication8th International Conference on Software Engineering and Computer Systems, ICSECS 2023
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages111-116
Number of pages6
ISBN (Electronic)9798350310931
DOIs
Publication statusPublished - 2023
Event8th IEEE International Conference on Software Engineering and Computer Systems, ICSECS 2023 - Penang, Malaysia
Duration: 25 Aug 202327 Aug 2023

Publication series

Name8th International Conference on Software Engineering and Computer Systems, ICSECS 2023

Conference

Conference8th IEEE International Conference on Software Engineering and Computer Systems, ICSECS 2023
Country/TerritoryMalaysia
CityPenang
Period25/08/2327/08/23

Fingerprint

Dive into the research topics of 'Determining the Optimal Number of GAT and GCN Layers for Node Classification in Graph Neural Networks'. Together they form a unique fingerprint.

Cite this