Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convo...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 2 vom: 15. Feb., Seite 783-798
1. Verfasser: Bai, Lu (VerfasserIn)
Weitere Verfasser: Cui, Lixin, Jiao, Yuhang, Rossi, Luca, Hancock, Edwin R
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM313260729
003 DE-627
005 20231225150210.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2020.3011866  |2 doi 
028 5 2 |a pubmed24n1044.xml 
035 |a (DE-627)NLM313260729 
035 |a (NLM)32750832 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bai, Lu  |e verfasserin  |4 aut 
245 1 0 |a Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 10.01.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN 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. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model 
650 4 |a Journal Article 
700 1 |a Cui, Lixin  |e verfasserin  |4 aut 
700 1 |a Jiao, Yuhang  |e verfasserin  |4 aut 
700 1 |a Rossi, Luca  |e verfasserin  |4 aut 
700 1 |a Hancock, Edwin R  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 44(2022), 2 vom: 15. Feb., Seite 783-798  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:44  |g year:2022  |g number:2  |g day:15  |g month:02  |g pages:783-798 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2020.3011866  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 44  |j 2022  |e 2  |b 15  |c 02  |h 783-798