An End-to-End Deep Learning Architecture for Graph Classification
An End-to-End Deep Learning Architecture for Graph Classification
复制标题
DOI：
10.1609/aaai.v32i1.11782
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Muhan Zhang;Zhicheng Cui;Marion Neumann;Yixin Chen
中科院分区：
文献类型：
--
作者：
Muhan Zhang;Zhicheng Cui;Marion Neumann;Yixin Chen
神经网络通常是用来处理张量形式的数据的。在本文中，我们提出了一种新的接受任意结构图的神经网络结构。给出一个包含(G，y)形式的图的数据集，其中G是图，y是它的类，我们的目标是开发直接读取图并学习分类函数的神经网络。主要有两个挑战：1)如何提取有用的特征来表征编码在图中的丰富信息以用于分类；2)如何以有意义和一致的顺序读取图。为了解决第一个挑战，我们设计了一个局部化的图卷积模型，并证明了它与两个图核之间的联系。为了解决第二个挑战，我们设计了一种新颖的SortPooling层，它以一致的顺序对图的顶点进行排序，以便传统的神经网络可以在图上进行训练。在基准图分类数据集上的实验表明，该体系结构与最新的图核和其他图神经网络方法相比具有很强的竞争力。此外，该体系结构允许使用原始图形进行端到端基于梯度的训练，而不需要首先将图形转换为矢量。
Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. Given a dataset containing graphs in the form of (G,y) where G is a graph and y is its class, we aim to develop neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs. Experiments on benchmark graph classification datasets demonstrate that the proposed architecture achieves highly competitive performance with state-of-the-art graph kernels and other graph neural network methods. Moreover, the architecture allows end-to-end gradient-based training with original graphs, without the need to first transform graphs into vectors.