arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.09173cs.LGcs.CVeess.IV
收藏

GFCN:一种新的基于并行流的图卷积网络

GFCN: A New Graph Convolutional Network Based on Parallel Flows

Nanyang Technological University(南洋理工大学)

Feng Ji, Jielong Yang, Qiang Zhang, Wee Peng Tay

摘要:

鉴于卷积神经网络(CNN)用于图像分类和对象识别的巨大成功,已经尝试将该方法推广到一般的图形结构数据。一个主要的研究方向是基于谱图理论和图信号处理。在本文中,我们从一个完全不同的角度来研究这个问题,通过引入图的并行流分解。其基本思想是将图分解为不相交的一维(1D)路径族,之后,我们可以沿着每个路径族应用1D CNN。我们证明了我们的方法,我们称之为GraphFlow,能够将CNN架构转换为一般图形。为了证明我们的方法的有效性,我们测试了我们的方法在经典的MNIST数据集,网络信息传播的合成数据集和新闻文章分类数据集。

英文摘要:

In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data. One major direction is based on spectral graph theory and graph signal processing. In this paper, we study the problem from a completely different perspective, by introducing parallel flow decomposition of graphs. The essential idea is to decompose a graph into families of non-intersecting one dimensional (1D) paths, after which, we may apply a 1D CNN along each family of paths. We demonstrate that the our method, which we call GraphFlow, is able to transfer CNN architectures to general graphs. To show the effectiveness of our approach, we test our method on the classical MNIST dataset, synthetic datasets on network information propagation and a news article classification dataset.

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。

↑