In EDS ansehen

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

Gespeichert in:
Bibliographische Detailangaben
Titel: On the approximation capability of GNNs in node classification/regression tasks.
Autoren: D'Inverno, Giuseppe Alessio, Bianchini, Monica, Sampoli, Maria Lucia, Scarselli, Franco
Quelle: Soft Computing - A Fusion of Foundations, Methodologies & Applications; Jul2024, Vol. 28 Issue 13/14, p8527-8547, 21p
Schlagwörter: GRAPH neural networks, DISCONTINUOUS functions, CLASSIFICATION
Abstract: 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 2 r - 1 , where r is the maximum number of nodes for the graphs in the domain. [ABSTRACT FROM AUTHOR]
Copyright of Soft Computing - A Fusion of Foundations, Methodologies & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Datenbank: Complementary Index
Beschreibung
Abstract: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 2 r - 1 , where r is the maximum number of nodes for the graphs in the domain. [ABSTRACT FROM AUTHOR]
ISSN:14327643
DOI:10.1007/s00500-024-09676-1