LWP-WL: link weight prediction based on CNNs and the Weisfeiler–Lehman algorithm

dc.contributor.authorZulaika Zurimendi, Unai
dc.contributor.authorSánchez Corcuera, Rubén
dc.contributor.authorAlmeida, Aitor
dc.contributor.authorLópez de Ipiña González de Artaza, Diego
dc.date.accessioned2024-11-07T10:24:52Z
dc.date.available2024-11-07T10:24:52Z
dc.date.issued2022-05-01
dc.date.updated2024-11-07T10:24:52Z
dc.description.abstractWe present a new technique for link weight prediction, the Link Weight Prediction Weisfeiler–Lehman (LWP-WL) method that learns from graph structure features and link relationship patterns. Inspired by the Weisfeiler–Lehman Neural Machine, LWP-WL extracts an enclosing subgraph for the target link and applies a graph labelling algorithm for weighted graphs to provide an ordered subgraph adjacency matrix into a neural network. The neural network contains a Convolutional Neural Network in the first layer that applies special filters adapted to the input graph representation. An extensive evaluation is provided that demonstrates an improvement over the state-of-the-art methods in several weighted graphs. Furthermore, we conduct an ablation study to show how adding different features to our approach improves our technique's performance. Finally, we also perform a study on the complexity and scalability of our algorithm. Unlike other approaches, LWP-WL does not rely on a specific graph heuristic and can perform well in different kinds of graphs.en
dc.description.sponsorshipWe gratefully acknowledge the support of the Basque Government's, Spain Department of Education for the predoctoral funding; the Ministry of Economy, Industry and Competitiveness of Spain under Grant No.: TIN2017-90042-R (SentientThings) and RTI2018-101045-A-C22 (FuturAAL). We would also like to thank NVIDIA for providing us their hardware via the Nvidia GPU Grant and the Basque Government for their Grant on scientific equipment adquisition with No. EC-19.en
dc.identifier.citationZulaika, U., Sánchez-Corcuera, R., Almeida, A., & López-de-Ipiña, D. (2022). LWP-WL: Link weight prediction based on CNNs and the Weisfeiler–Lehman algorithm. Applied Soft Computing, 120. https://doi.org/10.1016/J.ASOC.2022.108657
dc.identifier.doi10.1016/J.ASOC.2022.108657
dc.identifier.issn1568-4946
dc.identifier.urihttp://hdl.handle.net/20.500.14454/1688
dc.language.isoeng
dc.publisherElsevier Ltd
dc.rights© 2022 The Author(s)
dc.subject.otherGraph mining
dc.subject.otherLink weight prediction
dc.subject.otherWeisfeiler–Lehman algorithm
dc.titleLWP-WL: link weight prediction based on CNNs and the Weisfeiler–Lehman algorithmen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleApplied Soft Computing
oaire.citation.volume120
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Ficheros en el ítem
Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
zulaika_lwp_2022.pdf
Tamaño:
861.84 KB
Formato:
Adobe Portable Document Format
Colecciones