Empreu aquest identificador per citar o enllaçar aquest ítem:
http://hdl.handle.net/10609/150374
Títol: | Beyond Weisfeiler–Lehman with Local Ego-Network Encodings |
Autoria: | Alvarez-Gonzalez, Nurudin Kaltenbrunner, Andreas Gómez, Vicenç |
Citació: | Alvarez-Gonzalez, N, [Nurudin], Kaltenbrunner, A. [Andreas], Gómez, V. [Vicenç]. (2023). Beyond Weisfeiler–Lehman with Local Ego-Network Encodings. Machine Learning and Knowledge Extraction, 5(4). doi: 10.3390/make5040063 |
Resum: | Identifying similar network structures is key to capturing graph isomorphisms and learning representations that exploit structural information encoded in graph data. This work shows that ego networks can produce a structural encoding scheme for arbitrary graphs with greater expressivity than the Weisfeiler–Lehman (1-WL) test. We introduce IGEL, a preprocessing step to produce features that augment node representations by encoding ego networks into sparse vectors that enrich message passing (MP) graph neural networks (GNNs) beyond 1-WL expressivity. We formally describe the relation between IGEL and 1-WL, and characterize its expressive power and limitations. Experiments show that IGEL matches the empirical expressivity of state-of-the-art methods on isomorphism detection while improving performance on nine GNN architectures and six graph machine learning tasks. |
Paraules clau: | graph neural networks graph representation learning weisfeiler–lehman graph isomorphism GNN expressivity ego networks |
DOI: | https://doi.org/10.3390/make5040063 |
Tipus de document: | info:eu-repo/semantics/article |
Versió del document: | info:eu-repo/semantics/publishedVersion |
Data de publicació: | 22-set-2023 |
Llicència de publicació: | https://creativecommons.org/licenses/by/4.0/ |
Apareix a les col·leccions: | Articles cientÍfics Articles |
Arxius per aquest ítem:
Arxiu | Descripció | Mida | Format | |
---|---|---|---|---|
Beyond_Weisfeiler_Lehman_with_Local_Ego_Network_Encodings.pdf | 1,2 MB | Adobe PDF | Veure/Obrir |
Comparteix:
Els ítems del Repositori es troben protegits per copyright, amb tots els drets reservats, sempre i quan no s’indiqui el contrari.