arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.02709cs.LGcs.SIstat.ML
收藏

利用图神经网络的边缘特征

Exploiting Edge Features in Graph Neural Networks

University of Kentucky(肯塔基大学)

Liyu Gong, Qiang Cheng

摘要:

边特征包含有关图形的重要信息。然而,当前设计用于图学习的现有技术的神经网络模型,例如图卷积网络(GCN)和图注意力网络(GAT),充分利用边缘特征,特别是多维边缘特征。在本文中,我们建立了一个新的框架,一个家庭的新的图神经网络模型,可以更充分地利用边缘功能,包括那些无向或多维边缘。所提出的框架可以整合当前的图神经网络模型;例如,图卷积网络(GCN)和图注意力网络(GAT)。所提出的框架和新模型具有以下新颖性:首先,我们提出使用图边缘特征的双重随机归一化,而不是当前图神经网络中常用的行或对称归一化方法。其次,我们构造新的公式,在每个单独的层的操作,使他们能够处理多维的边缘功能。第三,对于所提出的新框架,边缘特征是跨网络层自适应的。因此,我们提出的新框架和新模型可以利用丰富的图形信息源。我们将我们的新模型应用于几个引文网络上的图节点分类、全图分类和几个分子数据集上的回归。与现有的GCN和GAT方法相比,该模型具有更好的性能,证明了利用边缘特征在图神经网络中的重要性.

英文摘要:

Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build a new framework for a family of new graph neural network models that can more sufficiently exploit edge features, including those of undirected or multi-dimensional edges. The proposed framework can consolidate current graph neural network models; e.g. graph convolutional networks (GCN) and graph attention networks (GAT). The proposed framework and new models have the following novelties: First, we propose to use doubly stochastic normalization of graph edge features instead of the commonly used row or symmetric normalization approches used in current graph neural networks. Second, we construct new formulas for the operations in each individual layer so that they can handle multi-dimensional edge features. Third, for the proposed new framework, edge features are adaptive across network layers. As a result, our proposed new framework and new models can exploit a rich source of graph information. We apply our new models to graph node classification on several citation networks, whole graph classification, and regression on several molecular datasets. Compared with the current state-of-the-art methods, i.e. GCNs and GAT, our models obtain better performance, which testify to the importance of exploiting edge features in graph neural networks.

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。

↑