Szczegóły publikacji
Opis bibliograficzny
Relation order histograms as a network embedding tool / Radosław ŁAZARZ, Michał IDZIK // W: Computational Science – ICCS 2021 : 21st international conference : Krakow, Poland, June 16–18, 2021 : proceedings, Pt. 2 / eds. Maciej Paszyński, [et al.]. — Cham : Springer Nature Switzerland, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12743. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-030-77963-4; e-ISBN: 978-3-030-77964-1. — S. 224–237. — Bibliogr., Abstr. — Publikacja dostępna online od: 2021-06-09
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 134718 |
|---|---|
| Data dodania do BaDAP | 2021-06-23 |
| DOI | 10.1007/978-3-030-77964-1_18 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | 21st International Conference on Computational Science |
| Czasopisma/serie | Lecture Notes in Computer Science, Theoretical Computer Science and General Issues |
Abstract
In this work, we introduce a novel graph embedding technique called NERO (Network Embedding based on Relation Order histograms). Its performance is assessed using a number of well-known classification problems and a newly introduced benchmark dealing with detailed laminae venation networks. The proposed algorithm achieves results surpassing those attained by other kernel-type methods and comparable with many state-of-the-art GNNs while requiring no GPU support and being able to handle relatively large input data. It is also demonstrated that the produced representation can be easily paired with existing model interpretation techniques to provide an overview of the individual edge and vertex influence on the investigated process.