Beyond Weisfeiler–Lehman with local ego-network encodings
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 Wei...
| Autores: | , , |
|---|---|
| Tipo de documento: | artigo |
| Estado: | Versão publicada |
| Data de publicação: | 2023 |
| País: | España |
| Recursos: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositório: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:10230/71827 |
| Acesso em linha: | http://hdl.handle.net/10230/71827 http://dx.doi.org/10.3390/make5040063 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Graph neural networks Graph representation learning Weisfeiler–Lehman Graph isomorphism GNN expressivity Ego networks |
| Resumo: | 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. |
|---|