skip to main content
10.1145/3488560.3502212acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
extended-abstract

GNNs for Node Clustering in Signed and Directed Networks

Published: 15 February 2022 Publication History

Abstract

With an increasing number of applications where data can be represented as graphs, graph neural networks are a useful tool to apply deep learning to graph data. In particular, node clustering is an important problem in network analysis. Signed and directed networks are important types of networks that are linked to many real-world problems; their asymmetry provides a challenge for many clustering methods.
We propose two graph neural network models for node clustering in signed networks and directed networks, respectively. The methods are end-to-end in combining embedding generation and clustering without an intermediate step. Experimental results on a synthetic signed stochastic block model, a polarized version of it, and real-world data at different scales, demonstrate that our proposed methods can achieve comparable or better results than state-of-the-art node clustering methods, for a wide range of noise and sparsity levels. The introduced models complement existing well-performing methods through the possibility of including exogenous information, in the form of node-level features or labels.

Supplementary Material

MP4 File (WSDM22-dc02.mp4)
Presentation video

References

[1]
A. Bovet and P. Grindrod. 2021. The Activity of the Far Right on Telegram . Complex Networks and its Applications .
[2]
M. Cucuringu et al. 2020. Hermitian matrices for clustering directed graphs: insights and applications. In AISTATS .
[3]
T. Derr et al. 2018. Signed graph convolutional networks. In ICDM. IEEE.
[4]
Y. He et al. 2021a. DIGRAC: Digraph Clustering with Flow Imbalance. arXiv preprint arXiv:2106.05194 (2021).
[5]
Y. He et al. 2021b. SSSNET: Semi-Supervised Signed Network Clustering. arXiv preprint arXiv:2110.06623 (2021).
[6]
M. Perry. 2003. State-to-state Migration Flows, 1995 to 2000. US Department of Commerce, Economics and Statistics Administration, US.
[7]
K. Read. 1954. Cultures of the central highlands, New Guinea. Southwestern Journal of Anthropology, Vol. 10, 1 (1954), 1--43.
[8]
M. Rosvall and C. Bergstrom. 2008. Maps of random walks on complex networks reveal community structure. Proc. of the Nat. Acad. of Sciences, Vol. 105, 4 (2008).
[9]
Y. Tian et al. 2019. Rethinking kernel methods for node representation learning on graphs. NeurIPS (2019).
[10]
Z. Tong et al. 2020. Digraph Inception Convolutional Networks. NeurIPS (2020).
[11]
Z. Wu et al. [n.,d.]. A Comprehensive Survey on Graph Neural Networks. IEEE Transactions on Neural Networks and Learning Systems ( [n.,d.]), 1--21.
[12]
J. Zhang et al. 2021a. Directed community detection with network embedding. J. Amer. Statist. Assoc. (2021), 1--11.
[13]
X. Zhang et al. 2021b. MagNet: A Neural Network for Directed Graphs. NeurIPS (2021).

Cited By

View all
  • (2023)Collaborative Graph Neural Networks for Attributed Network EmbeddingIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2023.329800236:3(972-986)Online publication date: 26-Jul-2023
  • (2022)Exploiting optimised communities in directed weighted graphs for link predictionOnline Social Networks and Media10.1016/j.osnem.2022.10022231(100222)Online publication date: Sep-2022

Index Terms

  1. GNNs for Node Clustering in Signed and Directed Networks

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
    February 2022
    1690 pages
    ISBN:9781450391320
    DOI:10.1145/3488560
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 15 February 2022

    Check for updates

    Author Tags

    1. directed networks
    2. graph neural networks
    3. signed networks

    Qualifiers

    • Extended-abstract

    Funding Sources

    • University of Oxford

    Conference

    WSDM '22

    Acceptance Rates

    Overall Acceptance Rate 498 of 2,863 submissions, 17%

    Upcoming Conference

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)61
    • Downloads (Last 6 weeks)6
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2023)Collaborative Graph Neural Networks for Attributed Network EmbeddingIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2023.329800236:3(972-986)Online publication date: 26-Jul-2023
    • (2022)Exploiting optimised communities in directed weighted graphs for link predictionOnline Social Networks and Media10.1016/j.osnem.2022.10022231(100222)Online publication date: Sep-2022

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media