Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 1 vom: 24. Jan., Seite 657-668
1. Verfasser: Bouritsas, Giorgos (VerfasserIn)
Weitere Verfasser: Frasca, Fabrizio, Zafeiriou, Stefanos, Bronstein, Michael M
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM337335370
003 DE-627
005 20250303015902.0
007 cr uuu---uuuuu
008 231225s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2022.3154319  |2 doi 
028 5 2 |a pubmed25n1124.xml 
035 |a (DE-627)NLM337335370 
035 |a (NLM)35201983 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bouritsas, Giorgos  |e verfasserin  |4 aut 
245 1 0 |a Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 05.04.2023 
500 |a Date Revised 05.04.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Leman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures. On the other hand, there is significant empirical evidence, e.g. in network science and bioinformatics, that substructures are often intimately related to downstream tasks. To this end, we propose "Graph Substructure Networks" (GSN), a topologically-aware message passing scheme based on substructure encoding. We theoretically analyse the expressive power of our architecture, showing that it is strictly more expressive than the WL test, and provide sufficient conditions for universality. Importantly, we do not attempt to adhere to the WL hierarchy; this allows us to retain multiple attractive properties of standard GNNs such as locality and linear network complexity, while being able to disambiguate even hard instances of graph isomorphism. We perform an extensive experimental evaluation on graph classification and regression tasks and obtain state-of-the-art results in diverse real-world settings including molecular graphs and social networks 
650 4 |a Journal Article 
700 1 |a Frasca, Fabrizio  |e verfasserin  |4 aut 
700 1 |a Zafeiriou, Stefanos  |e verfasserin  |4 aut 
700 1 |a Bronstein, Michael M  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 1 vom: 24. Jan., Seite 657-668  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:45  |g year:2023  |g number:1  |g day:24  |g month:01  |g pages:657-668 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2022.3154319  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 1  |b 24  |c 01  |h 657-668