arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00186cs.LGcs.DM
收藏

Sub-GMN:神经子图匹配网络模型

Sub-GMN: The Neural Subgraph Matching Network Model

Xi’an Jiaotong-Liverpool University(西交利物浦大学);The University of Liverpool(利物浦大学)

Zixun Lan, Limin Yu, Linglong Yuan, Zili Wu, Qiang Niu, Fei Ma

摘要:

子图匹配是图论中最基本的问题之一,在信息检索、计算机视觉、生物、化学和自然语言处理等领域都有重要的应用。然而,子图匹配问题仍然是一个NP完全问题。提出了一种基于端到端学习的子图匹配近似方法--子图匹配网络(Sub-GMN)。提出的Sub-GMN首先使用图表示学习将节点映射到节点级嵌入。然后,它结合了度量学习和注意力机制来建模数据图和查询图中匹配节点之间的关系。为了测试所提出的方法的性能,我们将我们的方法应用于两个数据库。我们使用两种现有的方法,GNN和FGNN作为基线进行比较。实验结果表明,在数据集1上,Sub-GMN的平均分类精度分别比GNN和FGNN高12.21%和3.2%。平均运行时间Sub-GMN比FGNN快20-40倍。此外,在数据集2的所有实验中,Sub-GMN的平均F1分数达到0.95,这表明Sub-GMN输出更正确的节点到节点匹配。与以前的基于GNNs的子图匹配方法相比,我们提出的Sub-GMN允许在测试/应用阶段改变查询和数据图,而大多数以前的基于GNNs的方法只能在测试/应用期间为训练阶段使用的相同查询图在数据图中找到匹配的子图。我们提出的Sub-GMN的另一个优点是它可以输出节点到节点匹配的列表,而大多数现有的基于端到端GNN的方法无法提供匹配的节点对。

英文摘要:

As one of the most fundamental tasks in graph theory, subgraph matching is a crucial task in many fields, ranging from information retrieval, computer vision, biology, chemistry and natural language processing. Yet subgraph matching problem remains to be an NP-complete problem. This study proposes an end-to-end learning-based approximate method for subgraph matching task, called subgraph matching network (Sub-GMN). The proposed Sub-GMN firstly uses graph representation learning to map nodes to node-level embedding. It then combines metric learning and attention mechanisms to model the relationship between matched nodes in the data graph and query graph. To test the performance of the proposed method, we applied our method on two databases. We used two existing methods, GNN and FGNN as baseline for comparison. Our experiment shows that, on dataset 1, on average the accuracy of Sub-GMN are 12.21\% and 3.2\% higher than that of GNN and FGNN respectively. On average running time Sub-GMN runs 20-40 times faster than FGNN. In addition, the average F1-score of Sub-GMN on all experiments with dataset 2 reached 0.95, which demonstrates that Sub-GMN outputs more correct node-to-node matches. Comparing with the previous GNNs-based methods for subgraph matching task, our proposed Sub-GMN allows varying query and data graphes in the test/application stage, while most previous GNNs-based methods can only find a matched subgraph in the data graph during the test/application for the same query graph used in the training stage. Another advantage of our proposed Sub-GMN is that it can output a list of node-to-node matches, while most existing end-to-end GNNs based methods cannot provide the matched node pairs.

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。

↑