SPAGAN:最短路径图注意力网络
SPAGAN: Shortest Path Graph Attention Network
摘要:
图卷积网络(GCN)最近已经证明了它们在分析可以表示为图的非网格结构数据中的潜力。其核心思想是通过卷积将图的局部拓扑编码为中心节点的特征。在本文中,我们提出了一种新的GCN模型,我们称之为最短路径图注意力网络(SPAGAN)。与传统的GCN模型,进行基于节点的注意力在每一层内,建议SPAGAN进行基于路径的注意力,明确占的一系列节点产生的最小成本,或最短路径,中心节点和它的高阶邻居之间的影响。因此,与基于节点的GCN方法相比,SPAGAN允许对图结构进行更多信息和完整的探索,并且进一步{a}更有效地将来自远距离邻居的信息聚合到中心节点中。我们在几个标准数据集上测试了SPAGAN的下游分类任务,并实现了优于现有技术的性能。代码可在https://github.com/ihollywhy/SPAGAN上公开获得。
英文摘要:
Graph convolutional networks (GCN) have recently demonstrated their potential in analyzing non-grid structure data that can be represented as graphs. The core idea is to encode the local topology of a graph, via convolutions, into the feature of a center node. In this paper, we propose a novel GCN model, which we term as Shortest Path Graph Attention Network (SPAGAN). Unlike conventional GCN models that carry out node-based attentions within each layer, the proposed SPAGAN conducts path-based attention that explicitly accounts for the influence of a sequence of nodes yielding the minimum cost, or shortest path, between the center node and its higher-order neighbors. SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods. We test SPAGAN on the downstream classification task on several standard datasets, and achieve performances superior to the state of the art. Code is publicly available at https://github.com/ihollywhy/SPAGAN.
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。