arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.08992cs.LGcs.CV
收藏

图神经网络在节点分类/回归任务中的逼近能力

On the approximation capability of GNNs in node classification/regression tasks

University of Siena(锡耶纳大学)

Giuseppe Alessio D'Inverno, Monica Bianchini, Maria Lucia Sampoli, Franco Scarselli

AI总结:

本文提出一种新方法证明GNNs在节点分类/回归任务中为概率通用逼近器,可逼近满足1-WL等价的可测函数,并给出所需层数上界$2r-1$。

摘要:

图神经网络(GNNs)是一类用于图处理的连接主义模型。近期研究表明,GNNs可以逼近图上的任意函数,但需模以由Weisfeiler--Lehman(WL)测试定义的图等价关系。然而,这些结果存在一些局限性,一方面是因为它们是通过Stone--Weierstrass定理推导的——该定理本质上是存在性的——另一方面是因为它们假设待逼近的目标函数必须是连续的。此外,目前所有结果都专注于图分类/回归任务,即GNN必须为整个图产生单一输出,而节点分类/回归问题(即为每个节点返回一个输出)也非常常见。在本文中,我们提出了一种替代方法来证明GNNs的逼近能力,从而克服这些局限性。实际上,我们证明了GNNs在节点分类/回归任务中是概率意义上的通用逼近器,因为它们可以逼近任何满足节点上1--WL等价的可测函数。所提出的理论框架允许逼近一般的非连续目标函数,并建议了能够达到期望逼近程度的GNN架构。此外,我们给出了达到期望逼近程度所需的GNN层数的界限,即$2r-1$,其中$r$是定义域中图的最大节点数。

英文摘要:

Graph Neural Networks (GNNs) are a broad class of connectionist models for graph processing. Recent studies have shown that GNNs can approximate any function on graphs, modulo the equivalence relation on graphs defined by the Weisfeiler--Lehman (WL) test. However, these results suffer from some limitations, both because they were derived using the Stone--Weierstrass theorem -- which is existential in nature, -- and because they assume that the target function to be approximated must be continuous. Furthermore, all current results are dedicated to graph classification/regression tasks, where the GNN must produce a single output for the whole graph, while also node classification/regression problems, in which an output is returned for each node, are very common. In this paper, we propose an alternative way to demonstrate the approximation capability of GNNs that overcomes these limitations. Indeed, we show that GNNs are universal approximators in probability for node classification/regression tasks, as they can approximate any measurable function that satisfies the 1--WL equivalence on nodes. The proposed theoretical framework allows the approximation of generic discontinuous target functions and also suggests the GNN architecture that can reach a desired approximation. In addition, we provide a bound on the number of the GNN layers required to achieve the desired degree of approximation, namely $2r-1$, where $r$ is the maximum number of nodes for the graphs in the domain.

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。

↑