We associate all small subgraph counting problems with a systematic graph encoding/representation system which makes a coherent use of graphlet structures. The system can serve as a unified foundation for studying and connecting many important graph problems in theory and practice. We describe topological relations among graphlets (graph elements) in rigorous mathematics language and from the perspective of graph encoding. We uncover, characterize and utilize algebraic and numerical relations in graphlet counts/frequencies. We present a novel algorithm for efficiently counting small subgraphs as a practical product of our theoretical findings.
Faster Algorithms for Finding and Counting Subgraphs
In this paper we study a natural generalization of both { \sc $k$ -Path} and { \sc $k$ -Tree} problems, namely, the { \sc Subgraph Isomorphism} problem. In the { \sc Subgraph Isomorphism} problem we are given two graphs $F$ and $G$ on $k$ and $n$ vertices respectively as an input, and the question is whether there exists a subgraph of $G$ isomorphic to $F$ . We show that if the treewidth of $F$ is at most $t$ , then there is a randomized algorithm for the { \sc Subgraph Isomorphism} problem running in time $\cO^*(2^k n^{2t})$ . To do so, we associate a new multivariate {Homomorphism polynomial…
New York University(纽约大学);Johns Hopkins University(约翰斯·霍普金斯大学)
检测和计算图中某些子结构的能力对于解决图结构数据的许多任务非常重要,特别是在计算化学和生物学以及社会网络分析的背景下。受此启发,我们建议通过计算属性图子结构的能力来研究图神经网络(GNN)的表达能力,扩展最近的工作,检查它们在图同构测试和函数逼近中的能力。我们区分两种类型的子结构计数:诱导子图计数和子图计数,并建立流行的GNN架构的积极和消极的答案。具体地说,我们证明了消息传递神经网络(MPNN),2-Weisfeiler-Lehman(2-WL)和2-不变图网络(2-IGN)不能执行由3个或更多节点组成的子结构的子图计数,但它们可以执行星形子结构的子图计数。作为中间步骤,我们证明了2-WL和2-IGN在区分非同构图方面是等价的,部分回答了Maron等人(2019)提出的一个公开问题。我们还证明了积极的结果为k-WL和k-IGN以及负面的结果为k-WL与有限的迭代次数。然后,我们进行实验,支持MPNN和2-IGN的理论结果。此外,受子结构计数的启发和Murphy et al.(2019)的启发,我们提出了局部关系池模型,并证明了它不仅对子结构计数有效,而且能够在分子预测任务上实现有竞争力的性能。