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

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

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

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.
Originalspracheenglisch
TitelComplex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020
Redakteure/-innenRosa M. Benito, Chantal Cherifi, Hocine Cherifi, Esteban Moro, Luis Mateus Rocha, Marta Sales-Pardo
ErscheinungsortCham
Herausgeber (Verlag)Springer International Publishing AG
Seiten15-26
Seitenumfang12
ISBN (Print)9783030653507
DOIs
PublikationsstatusVeröffentlicht - 5 Jan. 2021
Veranstaltung9th International Conference on Complex Networks and Their Applications: COMPLEX NETWORKS 2020 - Virtual, Madrid, Spanien
Dauer: 1 Dez. 20203 Dez. 2020

Publikationsreihe

NameStudies in Computational Intelligence
Band944
ISSN (Print)1860-949X
ISSN (elektronisch)1860-9503

Konferenz

Konferenz9th International Conference on Complex Networks and Their Applications
KurztitelCOMPLEX NETWORKS 2020
Land/GebietSpanien
OrtVirtual, Madrid
Zeitraum1/12/203/12/20

ASJC Scopus subject areas

  • Artificial intelligence

Fingerprint

Untersuchen Sie die Forschungsthemen von „On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren