Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/150374
Title: | Beyond Weisfeiler–Lehman with Local Ego-Network Encodings |
Author: | Alvarez-Gonzalez, Nurudin Kaltenbrunner, Andreas Gómez, Vicenç |
Citation: | 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 |
Abstract: | 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. |
Keywords: | graph neural networks graph representation learning weisfeiler–lehman graph isomorphism GNN expressivity ego networks |
DOI: | https://doi.org/10.3390/make5040063 |
Document type: | info:eu-repo/semantics/article |
Version: | info:eu-repo/semantics/publishedVersion |
Issue Date: | 22-Sep-2023 |
Publication license: | https://creativecommons.org/licenses/by/4.0/ |
Appears in Collections: | Articles cientÍfics Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Beyond_Weisfeiler_Lehman_with_Local_Ego_Network_Encodings.pdf | 1,2 MB | Adobe PDF | View/Open |
Share:
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.