skip to main content
10.1145/3627673.3679088acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
tutorial
Open access

Unifying Spectral and Spatial Graph Neural Networks

Published: 21 October 2024 Publication History

Abstract

In recent years, Graph Neural Networks (GNNs) have attracted considerable attention. However, the rapid emergence of diverse GNN models, each grounded in different theoretical foundations, complicates the model selection process, as these models are not easily understood within a unified framework. Initial GNNs were constructed using spectral theory, while others were developed based on spatial theory. This theoretical divergence makes direct comparisons difficult. Furthermore, the variety of models within each theoretical domain further complicates their evaluation. In this tutorial, we explore state-of-the-art GNNs and present a comprehensive framework that bridges the spatial and spectral domains, clarifying their interrelationship. This framework deepens our understanding of GNN operations. The tutorial delves into key paradigms, such as spatial and spectral methods, through a synthesis of spectral graph theory and approximation theory. We conduct an in-depth analysis of recent research advancements, addressing emerging issues like over-smoothing, using well-established GNN models to illustrate the universality of our framework.

References

[1]
2020. Graph Neural Networks: Models and Applications. https://cse.msu.edu/ mayao4/tutorials/aaai2020 [Online; accessed 5. Oct. 2023].
[2]
2021. Graph Representation Learning:Foundations, Methods, Applications and Systems. https://kdd2021graph.github.io [Online; accessed 5. Oct. 2023].
[3]
2023. GNNBook@2023. https://graph-neural-networks.github.io/tutorial_ijcai22.html [Online; accessed 5. Oct. 2023].
[4]
Deyu Bo, Xiao Wang, Yang Liu, Yuan Fang, Yawen Li, and Chuan Shi. 2023. A Survey on Spectral Graph Neural Networks. arXiv preprint arXiv:2302.05631 (2023).
[5]
Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. 2017. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine 34, 4 (2017), 18--42.
[6]
Z. Chen, F. Chen, R. Lai, X. Zhang, and C. Lu. 2018. Rational Neural Networks for Approximating Graph Convolution Operator on Jump Discontinuities. (2018), 59--68. https://doi.org/10.1109/ICDM.2018.00021
[7]
Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, and Chang-Tien Lu. 2023. Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks. Comput. Surveys (2023). https://doi.org/10.1145/3627816
[8]
Ron Levie, Wei Huang, Lorenzo Bucci, Michael M Bronstein, and Gitta Kutyniok. 2021. Transferability of Spectral Graph Convolutional Neural Networks. J. Mach. Learn. Res. 22 (2021), 272--1.
[9]
Guangyu Meng, Qisheng Jiang, Kaiqun Fu, Beiyu Lin, Chang-Tien Lu, and Zhqian Chen. 2022. Early Forecasting of the Impact of Traffic Accidents Using a Single Shot Observation. In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM). SIAM, 100--108.
[10]
Asif Salim and S Sumitra. 2022. Spectral graph convolutional neural networks in the context of regularization theory. IEEE Transactions on Neural Networks and Learning Systems (2022).

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management
October 2024
5705 pages
ISBN:9798400704369
DOI:10.1145/3627673
This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 October 2024

Check for updates

Author Tags

  1. approximation theory
  2. graph neural networks
  3. spectral method

Qualifiers

  • Tutorial

Funding Sources

Conference

CIKM '24
Sponsor:

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

CIKM '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 216
    Total Downloads
  • Downloads (Last 12 months)216
  • Downloads (Last 6 weeks)70
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media