Learning structural node representations on directed graphs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Many applications require identifying nodes that perform similar functions in a graph. Learning latent representations that capture such structural role information about nodes has recently gained a lot of attention. A state-of-the-art algorithm, struc2vec, generates such representations for the nodes of undirected networks. However, the algorithm is unable to handle directed, weighted networks. In this paper, we present struc2vec++, a generalization of the above algorithm to such types of networks. We evaluate struc2vec++ on real and synthetic networks. We show that taking into account edge directions greatly improves performance. We compare struc2vec++ against a recently proposed algorithm. Although struc2vec++ is in most cases outperformed by the competing algorithm, experiments in a variety of different scenarios demonstrate that it is much more memory efficient and it can better capture structural roles in the presence of noise.

Original languageEnglish
Title of host publicationComplex Networks and Their Applications VII - Volume 2 Proceedings The 7th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2018
EditorsLuca Maria Aiello, Hocine Cherifi, Pietro Lió, Luis M. Rocha, Chantal Cherifi, Renaud Lambiotte
PublisherSpringer Verlag
Pages132-144
Number of pages13
ISBN (Print)9783030054137
DOIs
Publication statusPublished - 1 Jan 2019
Event7th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2018 - Cambridge, United Kingdom
Duration: 11 Dec 201813 Dec 2018

Publication series

NameStudies in Computational Intelligence
Volume813
ISSN (Print)1860-949X

Conference

Conference7th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2018
Country/TerritoryUnited Kingdom
CityCambridge
Period11/12/1813/12/18

Keywords

  • Node embeddings
  • Role discovery
  • Structural identity

Fingerprint

Dive into the research topics of 'Learning structural node representations on directed graphs'. Together they form a unique fingerprint.

Cite this