arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.02653cs.LGstat.ML
收藏

当工作重要时:将经典网络结构转换为图CNN

When Work Matters: Transforming Classical Network Structures to Graph CNN

Southeast University(东南大学);Nanjing University of Science and Technology(南京理工大学)

Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhenyu Zhang, Jian Yang

摘要:

许多模式识别应用可以形成为从图结构的数据(包括社交网络、蛋白质交互网络、万维网数据、知识图谱等)学习。虽然卷积神经网络(CNN)促进了网格化图像/视频理解任务的巨大进步,但是非常有限的注意力已经致力于转换这些成功的网络结构(包括初始网、剩余网、密集网等)由于图的不规则性和复杂的几何拓扑结构(无序的顶点,不固定的相邻边/顶点数),在图上建立卷积网络。在本文中,我们的目标是通过将不同的经典网络结构转换为图CNN,特别是在基本的图识别问题中,对工作问题进行全面的分析。具体而言,我们首先回顾了一般的图CNN方法,特别是在其谱滤波操作的不规则图形数据。然后将ResNet、Inception和DenseNet的基本结构引入到图CNN中,并在图上构造了这些网络结构,分别命名为G_ResNet、G_Inception和G_DenseNet。特别是,它试图通过阐明这些经典网络结构的工作方式来帮助绘制CNN,并为选择适当的图网络框架提供指导。最后,我们在几个公共图数据集(包括社交网络和生物信息学数据集)上全面评估了这些不同网络结构的性能,并演示了不同网络结构如何在图识别任务中对图CNN起作用。

英文摘要:

Numerous pattern recognition applications can be formed as learning from graph-structured data, including social network, protein-interaction network, the world wide web data, knowledge graph, etc. While convolutional neural network (CNN) facilitates great advances in gridded image/video understanding tasks, very limited attention has been devoted to transform these successful network structures (including Inception net, Residual net, Dense net, etc.) to establish convolutional networks on graph, due to its irregularity and complexity geometric topologies (unordered vertices, unfixed number of adjacent edges/vertices). In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem. Specifically, we firstly review the general graph CNN methods, especially in its spectral filtering operation on the irregular graph data. We then introduce the basic structures of ResNet, Inception and DenseNet into graph CNN and construct these network structures on graph, named as G_ResNet, G_Inception, G_DenseNet. In particular, it seeks to help graph CNNs by shedding light on how these classical network structures work and providing guidelines for choosing appropriate graph network frameworks. Finally, we comprehensively evaluate the performance of these different network structures on several public graph datasets (including social networks and bioinformatic datasets), and demonstrate how different network structures work on graph CNN in the graph recognition task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑