论文阅读 [TPAMI-2022] Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Clas

论文阅读 [TPAMI-2022] Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

论文搜索(studyai.com)

搜索论文: Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

搜索论文: http://www.studyai.com/search/whole-site/?q=Learning+Backtrackless+Aligned-Spatial+Graph+Convolutional+Networks+for+Graph+Classification

关键字(Keywords)

Convolution; Adaptation models; Transforms; Convolutional neural networks; Standards; Feature extraction; Kernel; Graph convolutional networks; transitive vertex alignment; backtrackless walk

机器学习

图卷积网络

摘要(Abstract)

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification.

在本文中，我们开发了一种新的无回溯对齐空间图卷积网络（BASGCN）模型来学习用于图分类的有效特征。.

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.

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，并定义一种新的与网格结构相关的空间图卷积运算。.

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.

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，而且还弥补了传统卷积神经网络（CNN）模型和基于空间的GCN模型之间的理论差距。.

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.

此外，所提出的BASGCN模型既能在卷积过程中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中与Weisfeiler-Lehman算法相关的摇摇欲坠问题，说明了所提出模型的有效性。.

Experiments on standard graph datasets demonstrate the effectiveness of the proposed model…

在标准图形数据集上的实验证明了该模型的有效性。。.

作者(Authors)

[‘Lu Bai’, ‘Lixin Cui’, ‘Yuhang Jiao’, ‘Luca Rossi’, ‘Edwin R. Hancock’]