By the same authors

Learning Aligned-Spatial Graph Convolutional Networks for Graph Classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Full text download(s)

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

Title of host publicationMachine Learning and Knowledge Discovery in Databases
DatePublished - 30 Apr 2020
Pages464-482
Number of pages19
PublisherSpringer International Publishing
Place of PublicationCham
EditorsUlf Brefeld, Elisa Fromont, Andreas Hotho, Arno Knobbe, Marloes Maathuis, Céline Robardet
Original languageUndefined/Unknown
ISBN (Print)978-3-030-46150-8

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11906
ISSN (Print)0302-9743

Abstract

In this paper, we develop a novel Aligned-Spatial Graph Convolutional Network (ASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized aligned grid structures, and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed ASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Moreover, the proposed ASGCN model can adaptively discriminate the importance between specified vertices during the process of spatial graph convolution, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.

Bibliographical note

© Springer Nature Switzerland AG 2020. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations