An end-to-end graph convolutional kernel support vector machine

Corcoran, Padraig ORCID: https://orcid.org/0000-0001-9731-3385 2020. An end-to-end graph convolutional kernel support vector machine. Applied Network Science 5 , 39. 10.1007/s41109-020-00282-2

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (548kB) | Preview

Abstract

A novel kernel-based support vector machine (SVM) for graph classification is proposed. The SVM feature space mapping consists of a sequence of graph convolutional layers, which generates a vector space representation for each vertex, followed by a pooling layer which generates a reproducing kernel Hilbert space (RKHS) representation for the graph. The use of a RKHS offers the ability to implicitly operate in this space using a kernel function without the computational complexity of explicitly mapping into it. The proposed model is trained in a supervised end-to-end manner whereby the convolutional layers, the kernel function and SVM parameters are jointly optimized with respect to a regularized classification loss. This approach is distinct from existing kernel-based graph classification models which instead either use feature engineering or unsupervised learning to define the kernel function. Experimental results demonstrate that the proposed model outperforms existing deep learning baseline models on a number of datasets.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer
ISSN:	2364-8228
Date of First Compliant Deposit:	15 July 2020
Date of Acceptance:	7 July 2020
Last Modified:	05 May 2023 01:25
URI:	https://orca.cardiff.ac.uk/id/eprint/133332

Actions (repository staff only)

Edit Item