On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks

Hussain Hussain*, Tomislav Duricic, Elisabeth Lex, Roman Kern, Denis Helic

*Corresponding author for this work

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


Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. In this work, we systematically study the impact of community structure on the performance of GNNs in semi-supervised node classification on graphs. Following an ablation study on six datasets, we measure the performance of GNNs on the original graphs, and the change in performance in the presence and the absence of community structure. Our results suggest that communities typically have a major impact on the learning process and classification performance. For example, in cases where the majority of nodes from one community share a single classification label, breaking up community structure results in a significant performance drop. On the other hand, for cases where labels show low correlation with communities, we find that the graph structure is rather irrelevant to the learning process, and a feature-only baseline becomes hard to beat. With our work, we provide deeper insights in the abilities and limitations of GNNs, including a set of general guidelines for model selection based on the graph structure.
Original languageEnglish
Title of host publicationComplex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020
EditorsRosa M. Benito, Chantal Cherifi, Hocine Cherifi, Esteban Moro, Luis Mateus Rocha, Marta Sales-Pardo
Place of PublicationCham
PublisherSpringer International Publishing AG
Number of pages12
ISBN (Print)9783030653507
Publication statusPublished - 5 Jan 2021
Event9th International Conference on Complex Networks and Their Applications: COMPLEX NETWORKS 2020 - Virtual, Madrid, Spain
Duration: 1 Dec 20203 Dec 2020

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503


Conference9th International Conference on Complex Networks and Their Applications
Abbreviated titleCOMPLEX NETWORKS 2020
CityVirtual, Madrid


  • Community structure
  • Graph neural networks
  • Semi-supervised learning

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this