Journal article icon

Journal article

Learning graph representations with maximal cliques

Abstract:

Non-Euclidean property of graph structures has faced interesting challenges when deep learning methods are applied. Graph convolutional networks (GCNs) can be regarded as one of the successful approaches to classification tasks on graph data, although the structure of this approach limits its performance. In this work, a novel representation learning approach is introduced based on spectral convolutions on graph-structured data in a semisupervised learning setting. Our proposed method, COnvOl...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/TNNLS.2021.3104901

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0003-1074-3492
More by this author
Role:
Author
ORCID:
0000-0002-4229-1542
More by this author
Role:
Author
ORCID:
0000-0001-6559-0601
More by this author
Role:
Author
ORCID:
0000-0002-0517-9420
More by this author
Role:
Author
ORCID:
0000-0003-0794-527X
Publisher:
IEEE
Journal:
IEEE Transactions on Neural Networks and Learning Systems More from this journal
Volume:
34
Issue:
2
Pages:
1089-1096
Publication date:
2021-08-26
Acceptance date:
2021-08-11
DOI:
EISSN:
2162-2388
ISSN:
2162-237X
Language:
English
Keywords:
Pubs id:
1336304
Local pid:
pubs:1336304
Deposit date:
2023-04-25

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP