arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.00967cs.LGstat.ML
收藏

连续图神经网络

Continuous Graph Neural Networks

Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);University of Montréal(蒙特利尔大学);HEC Montréal(蒙特利尔高等商学院)

Louis-Pascal A. C. Xhonneux, Meng Qu, Jian Tang

摘要:

本文建立在图神经网络和传统的动力系统之间的联系。我们提出了连续图神经网络(CGNN),它概括了现有的图神经网络与离散动态,因为它们可以被看作是一个特定的离散化方案。其关键思想是如何描述节点表示的连续动态,即节点表示的导数,w.r.t.时间受图上现有的基于扩散的方法(例如社交网络上的PageRank和流行病模型)的启发,我们将导数定义为当前节点表示、邻居表示和节点初始值的组合。我们提出并分析了两种可能的动态图-包括每个维度的节点表示(a.k.a.特征通道)独立变化或相互作用-两者都有理论依据。所提出的连续图神经网络对过度平滑具有鲁棒性,因此允许我们构建更深的网络,从而能够捕获节点之间的长程依赖关系。节点分类任务的实验结果表明,我们所提出的方法的有效性,竞争力的基线。

英文摘要:

This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations, the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs---including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other---both with theoretical justification. The proposed continuous graph neural networks are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines.

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。

↑