Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 2, Pages 783-798Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.3011866
Keywords
Convolution; Adaptation models; Transforms; Convolutional neural networks; Standards; Feature extraction; Kernel; Graph convolutional networks; transitive vertex alignment; backtrackless walk
Funding
- National Natural Science Foundation of China [61976235, 61602535]
- program for innovation research in Central University of Finance and Economics
- Youth Talent Development Support Program by Central University of Finance and Economics [QYP1908]
Ask authors/readers for more resources
In this paper, a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model is proposed for learning effective features for graph classification. This model addresses the issues of information loss and imprecise information representation in existing spatially-based graph convolutional network (GCN) models, and bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models. Experimental results demonstrate the effectiveness of the proposed model.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available