Constructing graph node embeddings via discrimination of similarity distributions

Maxim Panov, Stanislav Tsepa

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

    1 Citation (Scopus)

    Abstract

    The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science. In this work we propose a novel framework, which is aimed to find embeddings by discriminating distributions of similarities (DDoS) between nodes in the graph. The general idea is implemented by maximizing the earth mover distance between distributions of decoded similarities of similar and dissimilar nodes. The resulting algorithm generates embeddings which give a state-of-the-art performance in the problem of link prediction in real-world graphs.

    Original languageEnglish
    Title of host publicationProceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
    EditorsZhenhui Li, Hanghang Tong, Jeffrey Yu, Feida Zhu
    PublisherIEEE Computer Society
    Pages1050-1053
    Number of pages4
    ISBN (Electronic)9781538692882
    DOIs
    Publication statusPublished - 7 Feb 2019
    Event18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 - Singapore, Singapore
    Duration: 17 Nov 201820 Nov 2018

    Publication series

    NameIEEE International Conference on Data Mining Workshops, ICDMW
    Volume2018-November
    ISSN (Print)2375-9232
    ISSN (Electronic)2375-9259

    Conference

    Conference18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
    Country/TerritorySingapore
    CitySingapore
    Period17/11/1820/11/18

    Keywords

    • Graph node embeddings
    • link prediction
    • representation learning
    • unsupervised learning
    • Wasserstein distance

    Fingerprint

    Dive into the research topics of 'Constructing graph node embeddings via discrimination of similarity distributions'. Together they form a unique fingerprint.

    Cite this