Bai Lu, Cui Lixin, Jiao Yuhang, Rossi Luca, Hancock Edwin R
IEEE Trans Pattern Anal Mach Intell. 2022 Feb;44(2):783-798. doi: 10.1109/TPAMI.2020.3011866. Epub 2022 Jan 7.
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.
在本文中，我们开发了一种新颖的无回溯对齐空间图卷积网络（BASGCN）模型，用于学习图分类的有效特征。我们的想法是将任意大小的图转换为固定大小的无回溯对齐网格结构，并定义一种与网格结构相关的新的空间图卷积操作。我们表明，所提出的BASGCN模型不仅减少了现有基于空间的图卷积网络（GCN）模型中出现的信息丢失和信息表示不精确的问题，还弥合了传统卷积神经网络（CNN）模型与基于空间的GCN模型之间的理论差距。此外，所提出的BASGCN模型在卷积过程中既能自适应地区分指定顶点之间的重要性，又能减少现有基于空间的GCN与魏斯费勒 - 莱曼算法相关的臭名昭著的抖动问题，解释了所提模型的有效性。在标准图数据集上的实验证明了所提模型的有效性。
