Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/89323
PIRA download icon_1.1View/Download Full Text
Title: Multi-channel graph neural networks
Authors: Zhou, K
Song, Q
Huang, X 
Zha, D
Zou, N
Hu, X
Issue Date: 2020
Source: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), Yokohama, Japan, January 2021, p. 1352-1358
Abstract: The classification of graph-structured data has become increasingly crucial in many disciplines. It has been observed that the implicit or explicit hierarchical community structures preserved in realworld graphs could be useful for downstream classification applications. A straightforward way to leverage the hierarchical structures is to make use of pooling algorithm to cluster nodes into fixed groups, and shrink the input graph layer by layer to learn the pooled graphs. However, the pool shrinking discards graph details to make it hard to distinguish two non-isomorphic graphs, and the fixed clustering ignores the inherent multiple characteristics of nodes. To compensate the shrinking loss and learn the various nodes’ characteristics, we propose the multi-channel graph neural networks (MuchGNN). Motivated by the underlying mechanisms developed in convolutional neural networks, we define the tailored graph convolutions to learn a series of graph channels at each layer, and shrink the graphs hierarchically to encode the pooled structures. Experimental results on real-world datasets demonstrate the superiority of MuchGNN over the state-of-the-art methods.
Publisher: International Joint Conferences on Artificial Intelligence
ISBN: 978-0-9992411-6-5
Rights: Copyright © 2020 International Joint Conferences on Artificial Intelligence
All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher.
Posted with permission of the author.
The following publication Zhou, K., Song, Q., Huang, X., Zha, D., Zou, N., & Hu, X. (2021, January). Multi-channel graph neural networks. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), Yokohama, Japan, 1352-1358 is available at https://www.ijcai.org/Proceedings/2020/
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
IJCAI_MuchGNN.pdf534.9 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Other Version
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

92
Citations as of May 29, 2022

Downloads

84
Citations as of May 29, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.