arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.13679cs.LG
收藏

SeedGNN:用于监督式种子图匹配的图神经网络

SeedGNN: Graph Neural Networks for Supervised Seeded Graph Matching

Purdue University(普渡大学);Duke University(杜克大学)

Liren Yu, Jiaming Xu, Xiaojun Lin

AI总结:

本文提出监督式图神经网络SeedGNN,通过可迁移的见证信息计算和利用易匹配节点对作为新种子,实现仅用少量种子即可匹配未见图,并在合成与真实图上显著优于现有方法。

摘要:

人们对设计用于种子图匹配的图神经网络(GNNs)越来越感兴趣,该任务旨在仅利用拓扑信息和少量种子节点来匹配两个无标签图。然而,以往用于此任务的大多数GNN采用半监督方法,需要大量种子,并且无法学习可迁移到未见过的图的知识。相比之下,本文提出了一种新的监督方法,可以从训练集中学习如何仅用少量种子匹配未见过的图。我们的SeedGNN架构融合了若干受种子图匹配理论研究启发的新设计:1)它能够学习计算和利用来自不同跳数的类似见证(witness)的信息,其方式可推广到不同规模的图;2)它能够利用容易匹配的节点对作为新的种子,以改进后续层中的匹配。我们在合成图和真实世界图上评估了SeedGNN,并证明其性能显著优于现有文献中的非学习算法和学习算法。此外,我们的实验证实,SeedGNN从训练图中学到的知识可以推广到不同规模和类别的测试图。

英文摘要:

There is a growing interest in designing Graph Neural Networks (GNNs) for seeded graph matching, which aims to match two unlabeled graphs using only topological information and a small set of seed nodes. However, most previous GNNs for this task use a semi-supervised approach, which requires a large number of seeds and cannot learn knowledge that is transferable to unseen graphs. In contrast, this paper proposes a new supervised approach that can learn from a training set how to match unseen graphs with only a few seeds. Our SeedGNN architecture incorporates several novel designs, inspired by theoretical studies of seeded graph matching: 1) it can learn to compute and use witness-like information from different hops, in a way that can be generalized to graphs of different sizes; 2) it can use easily-matched node-pairs as new seeds to improve the matching in subsequent layers. We evaluate SeedGNN on synthetic and real-world graphs and demonstrate significant performance improvements over both non-learning and learning algorithms in the existing literature. Furthermore, our experiments confirm that the knowledge learned by SeedGNN from training graphs can be generalized to test graphs of different sizes and categories.

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。

↑