arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.01190cs.LGcs.AI
收藏

两层图神经网络

Two-level Graph Neural Network

Xiamen University(厦门大学);University of York(约克大学)

Xing Ai, Chengyu Sun, Zhihong Zhang, Edwin R Hancock

摘要:

图神经网络(GNN)是最近提出的用于处理图结构数据的神经网络结构。现有的GNN由于采用了邻居聚合策略,只注重获取节点级信息,而忽略了高层信息。因此,现有的GNN遭受由局部排列不变性(LPI)问题引起的代表性限制。为了克服这些限制并丰富GNN捕获的功能,我们提出了一种新的GNN框架,称为两级GNN(TL-GNN)。这将子图级信息与节点级信息合并。此外,我们提供了一个数学分析的LPI问题,这表明,子图级的信息是有益的,以克服与LPI相关的问题。提出了一种基于动态规划算法的子图计数方法,该方法的时间复杂度为O(n^3),n为图的节点数。实验表明,TL-GNN优于现有的GNN,并达到最先进的性能。

英文摘要:

Graph Neural Networks (GNNs) are recently proposed neural network structures for the processing of graph-structured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information. Existing GNNs therefore suffer from representational limitations caused by the Local Permutation Invariance (LPI) problem. To overcome these limitations and enrich the features captured by GNNs, we propose a novel GNN framework, referred to as the Two-level GNN (TL-GNN). This merges subgraph-level information with node-level information. Moreover, we provide a mathematical analysis of the LPI problem which demonstrates that subgraph-level information is beneficial to overcoming the problems associated with LPI. A subgraph counting method based on the dynamic programming algorithm is also proposed, and this has time complexity is O(n^3), n is the number of nodes of a graph. Experiments show that TL-GNN outperforms existing GNNs and achieves state-of-the-art performance.

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。

↑