On Joint Representation Learning of Network Structure and Document Content

Jörg Schlötterer, Christin Seifert, Michael Granitzer

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

    3 Citations (Scopus)

    Abstract

    Inspired by the advancements of representation learning for natural language processing, learning continuous feature representations of nodes in networks has recently gained attention. Similar to word embeddings, node embeddings have been shown to capture certain semantics of the network structure. Combining both research directions into a joint representation learning of network structure and document content seems a promising direction to increase the quality of the learned representations. However, research is typically focused on either word or network embeddings and few approaches that learn a joint representation have been proposed. We present an overview of that field, starting at word representations, moving over document and network node representations to joint representations. We make the connections between the different models explicit and introduce a novel model for learning a joint representation. We present different methods for the novel model and compare the presented approaches in an evaluation. This paper explains how the different models recently proposed in the literature relate to each other and compares their performance.
    Original languageEnglish
    Title of host publicationMachine Learning and Knowledge Extraction
    Subtitle of host publicationFirst IFIP TC 5, WG 8.4, 8.9, 12.9 International Cross-Domain Conference, CD-MAKE 2017, Reggio, Italy, August 29 – September 1, 2017, Proceedings
    EditorsAndreas Holzinger, Peter Kieseberg, A. Min Tjoa, Edgar Weippl
    PublisherSpringer
    Pages237-251
    ISBN (Electronic)978-3-319-66808-6
    ISBN (Print)978-3-319-66807-9
    DOIs
    Publication statusPublished - 2017
    Event1st International IFIP Cross Domain Conference for Machine Learning & Knowledge Extraction 2017 - Reggio di Calabria, Italy
    Duration: 29 Aug 20171 Sep 2017
    Conference number: 1
    https://cd-make.net/archive2017/call-for-papers/index.html

    Publication series

    NameLecture notes in computer science
    PublisherSpringer
    Volume10410

    Conference

    Conference1st International IFIP Cross Domain Conference for Machine Learning & Knowledge Extraction 2017
    Abbreviated titleCD-MAKE 2017
    CountryItaly
    CityReggio di Calabria
    Period29/08/171/09/17
    Internet address

    Fingerprint Dive into the research topics of 'On Joint Representation Learning of Network Structure and Document Content'. Together they form a unique fingerprint.

    Cite this