Graph Classification of Graph Neural Networks

View Sample PDF

Author(s): Gotam Singh Lalotra (Government Degree College, Basohli, India), Ashok Sharma (University of Jammu, India), Barun Kumar Bhatti (Government Degree College for Women, Kathua, India)and Suresh Singh (GGM Science College, Jammu, India)
Copyright: 2023
Pages: 15
Source title: Concepts and Techniques of Graph Neural Networks
Source Author(s)/Editor(s): Vinod Kumar (Koneru Lakshmaiah Education Foundation (Deemed), India)and Dharmendra Singh Rajput (VIT University, India)
DOI: 10.4018/978-1-6684-6903-3.ch004

Keywords: Artificial Intelligence / Computer Science & IT / Engineering Science Reference / Neural Networks

Purchase

View Graph Classification of Graph Neural Networks on the publisher's website for pricing and purchasing information.

Abstract

Graph neural networks have recently come to the fore as the top machine learning architecture for supervised learning using graph and relational data. An overview of GNNs for graph classification (i.e., GNNs that learn a graph level output) is provided in this chapter as pooling layers, or layers that learn graph-level representations from node-level representations, are essential elements for successful graph classification because GNNs compute node-level representations. Hence, the authors give a thorough overview of pooling layers. The constraints of GNNs for graph categorization are further discussed, along with developments made in overcoming them. Finally, they review some GNN applications for graph classification and give an overview of benchmark datasets for empirical analysis.

The IRMA Community

Research IRM

Graph Classification of Graph Neural Networks

Purchase

Abstract

Related Content

IRMA Sponsors