Attentive Walk-Aggregating Graph Neural Networks

Attentive Walk-Aggregating Graph Neural Networks
复制标题

DOI:
--
复制
发表时间:
2021-10
期刊:
Trans. Mach. Learn. Res.
影响因子:
--
通讯作者:
M. F. Demirel;Shengchao Liu;Siddhant Garg;Zhenmei Shi;Yingyu Liang
M. F. Demirel;Shengchao Liu;Siddhant Garg;Zhenmei Shi;Yingyu Liang
中科院分区:
其他
文献类型:
--
作者:
M. F. Demirel;Shengchao Liu;Siddhant Garg;Zhenmei Shi;Yingyu Liang

文献摘要

相似文献

图神经网络(Graph neural networks,GNNs)已被证明具有强大的表征能力,可用于图结构数据(如分子和社交网络)的下游预测任务。它们通常通过聚合来自单个顶点的$K$跳邻域或图中枚举路径的信息来学习表征。先前的研究已经证明了在GNNs中纳入加权方案的有效性;然而,到目前为止,这主要局限于$K$跳邻域GNNs。在本文中,我们旨在设计一种将加权方案纳入路径聚合GNNs的算法,并分析其效果。我们提出了一种新的GNN模型,称为AWARE,它使用注意力机制聚合图中路径的信息。这导致了一种在标准设置下用于图级预测任务的端到端监督学习方法,其中输入是图的邻接信息和顶点信息,输出是图的预测标签。然后我们对AWARE进行理论、实证和可解释性分析。我们在简化设置下的理论分析确定了可证明保证的成功条件,展示了图信息如何在表征中编码,以及AWARE中的加权方案如何影响表征和学习性能。我们的实验证明了AWARE在分子性质预测和社交网络领域的标准设置下的图级预测任务中具有强大的性能。最后,我们的解释性研究表明AWARE能够成功捕获输入图的重要子结构。代码可在\(\href{https://github.com/mehmetfdemirel/aware}{GitHub}\)上获取。
Graph neural networks (GNNs) have been shown to possess strong representation power, which can be exploited for downstream prediction tasks on graph-structured data, such as molecules and social networks. They typically learn representations by aggregating information from the $K$-hop neighborhood of individual vertices or from the enumerated walks in the graph. Prior studies have demonstrated the effectiveness of incorporating weighting schemes into GNNs; however, this has been primarily limited to $K$-hop neighborhood GNNs so far. In this paper, we aim to design an algorithm incorporating weighting schemes into walk-aggregating GNNs and analyze their effect. We propose a novel GNN model, called AWARE, that aggregates information about the walks in the graph using attention schemes. This leads to an end-to-end supervised learning method for graph-level prediction tasks in the standard setting where the input is the adjacency and vertex information of a graph, and the output is a predicted label for the graph. We then perform theoretical, empirical, and interpretability analyses of AWARE. Our theoretical analysis in a simplified setting identifies successful conditions for provable guarantees, demonstrating how the graph information is encoded in the representation, and how the weighting schemes in AWARE affect the representation and learning performance. Our experiments demonstrate the strong performance of AWARE in graph-level prediction tasks in the standard setting in the domains of molecular property prediction and social networks. Lastly, our interpretation study illustrates that AWARE can successfully capture the important substructures of the input graph. The code is available on $\href{https://github.com/mehmetfdemirel/aware}{GitHub}$.