Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
This addresses graph classification for researchers and practitioners by reducing information loss and tottering in existing GCNs, though it appears incremental as it builds on spatially-based GCNs.
The paper tackles the problem of graph classification by developing a Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) that transforms graphs into fixed-sized grid structures and defines a new spatial convolution operation, resulting in improved performance on standard datasets.
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.