dyngraph2vec: Capturing network dynamics using dynamic graph representation learning

Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real-world networks evolve over time and have varying dynamics. Capturing such evolution is key to pr...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Knowledge-based systems Ročník 187; s. 104816
Hlavní autori:	Goyal, Palash, Chhetri, Sujit Rokka, Canedo, Arquimedes
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Amsterdam Elsevier B.V 01.01.2020 Elsevier Science Ltd
Predmet:	Datasets Dynamics Efficacy Embedding Evolution Graph embedding applications Graph embedding techniques Graph representations Graphical representations Graphs Learning Machine learning Networks Performance prediction Predictions Property Python graph embedding methods GEM library Recurrent Stochastic models Python graph embedding methods GEM library Graph embedding applications Graph embedding techniques
ISSN:	0950-7051, 1872-7409
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real-world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need for capturing dynamics for the prediction on a toy dataset created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real-world datasets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0950-7051 1872-7409
DOI:	10.1016/j.knosys.2019.06.024