Experimental investigation of neural and Weisfeiler-Lehman-Kernel graph representations for downstream SVM-based classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F21%3A00382640" target="_blank" >RIV/68407700:21240/21:00382640 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/67985807:_____/21:00546251 RIV/68407700:21340/21:00382640

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Experimental investigation of neural and Weisfeiler-Lehman-Kernel graph representations for downstream SVM-based classification

Popis výsledku v původním jazyce

Graphs are one of the most ubiquitous kinds of data. However, data analysis methods have been developed primarily for numerical data, and to make use of them, graphs need to be represented as elements of some Euclidean space. An increasingly popular way of representing them in this way are graph neural networks (GNNs). Because data analysis applications typically require identical results for isomorphic graphs, the representations learned by GNNs also need to be invariant with respect to graph isomorphism. That motivated recent research into the possibilities of recognizing nonisomorphic pairs of graphs by GNNs, primarily based on the Weisfeiler-Lehman (WL) isomorphism test. This paper reports the results of a first experimental comparison of four variants of two important GNNs based on the WL test from the point of view of graph representation for downstream classification by means of a support vector machins (SVM). Those methods are compared not only with each other, but also with a recent generalization of the WL subtree kernel. For all GNN variants, two different representations are included in the comparison. The comparison revealed that the four considered representations of the same kind of GNN never significantly differ. On the other hand, there was always a statistically significant difference between representations originating from different kinds of GNNs, as well as between any representation originating from any of the considered GNNs and the representation originating from the generalized WL kernel.

Název v anglickém jazyce

Experimental investigation of neural and Weisfeiler-Lehman-Kernel graph representations for downstream SVM-based classification

Popis výsledku anglicky

Graphs are one of the most ubiquitous kinds of data. However, data analysis methods have been developed primarily for numerical data, and to make use of them, graphs need to be represented as elements of some Euclidean space. An increasingly popular way of representing them in this way are graph neural networks (GNNs). Because data analysis applications typically require identical results for isomorphic graphs, the representations learned by GNNs also need to be invariant with respect to graph isomorphism. That motivated recent research into the possibilities of recognizing nonisomorphic pairs of graphs by GNNs, primarily based on the Weisfeiler-Lehman (WL) isomorphism test. This paper reports the results of a first experimental comparison of four variants of two important GNNs based on the WL test from the point of view of graph representation for downstream classification by means of a support vector machins (SVM). Those methods are compared not only with each other, but also with a recent generalization of the WL subtree kernel. For all GNN variants, two different representations are included in the comparison. The comparison revealed that the four considered representations of the same kind of GNN never significantly differ. On the other hand, there was always a statistically significant difference between representations originating from different kinds of GNNs, as well as between any representation originating from any of the considered GNNs and the representation originating from the generalized WL kernel.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 21st Conference Information Technologies – Applications and Theory (ITAT 2021)

ISBN

—

ISSN

1613-0073

e-ISSN

1613-0073

Počet stran výsledku

10

Strana od-do

130-139

Název nakladatele

CEUR Workshop Proceedings

Místo vydání

Aachen

Místo konání akce

Heľpa

Datum konání akce

24. 9. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—