A capsule network-based model for learning node embeddings

Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung

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

5 Citations (Scopus)


In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE - a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target node at the first capsule layer, then feed these features into the second capsule layer to infer a plausible embedding for the target node. Experimental results show that our proposed Caps2NE obtains state-of-the-art performances on benchmark datasets for the node classification task. Our code is available at: https://github.com/daiquocnguyen/Caps2NE.

Original languageEnglish
Title of host publicationProceedings of the 29th ACM International Conference on Information & Knowledge Management
EditorsClaudia Hauff, Edward Curry, Philippe Cudre Mauroux
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages4
ISBN (Electronic)9781450368599
Publication statusPublished - 2020
EventACM International Conference on Information and Knowledge Management 2020 - Virtual, Online, Ireland
Duration: 19 Oct 202023 Oct 2020
Conference number: 29th
https://dl.acm.org/doi/proceedings/10.1145/3340531 (Proceedings)
https://www.cikm2020.org/ (Website)


ConferenceACM International Conference on Information and Knowledge Management 2020
Abbreviated titleCIKM 2020
CityVirtual, Online
Internet address


  • capsule networks
  • graph representation learning
  • node classification
  • node embeddings

Cite this