IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i11p2515-d1159700.html
   My bibliography  Save this article

Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data

Author

Listed:
  • Anna Boronina

    (Center for Technologies in Robotics and Mechatronics Components, Innopolis University, 420500 Innopolis, Russia)

  • Vladimir Maksimenko

    (Center for Technologies in Robotics and Mechatronics Components, Innopolis University, 420500 Innopolis, Russia
    Engineering School of Information Technologies, Telecommunications and Control Systems, Ural Federal University, 620002 Ekaterinburg, Russia)

  • Alexander E. Hramov

    (Engineering School of Information Technologies, Telecommunications and Control Systems, Ural Federal University, 620002 Ekaterinburg, Russia
    Baltic Center for Neurotechnology and Artificial Intelligence, Immanuel Kant Baltic Federal University, 236041 Kaliningrad, Russia)

Abstract

Applying machine learning algorithms to graph-structured data has garnered significant attention in recent years due to the prevalence of inherent graph structures in real-life datasets. However, the direct application of traditional deep learning algorithms, such as Convolutional Neural Networks (CNNs), is limited as they are designed for regular Euclidean data like 2D grids and 1D sequences. In contrast, graph-structured data are in a non-Euclidean form. Graph Neural Networks (GNNs) are specifically designed to handle non-Euclidean data and make predictions based on connectivity rather than spatial structure. Real-life graph data can be broadly categorized into two types: spatially-invariant graphs, where the link structure between nodes is independent of their spatial positions, and spatially-variant graphs, where node positions provide additional information about the graph’s properties. However, there is limited understanding of the effect of spatial variance on the performance of Graph Neural Networks. In this study, we aim to address this issue by comparing the performance of GNNs and CNNs on spatially-variant and spatially-invariant graph data. In the case of spatially-variant graphs, when represented as adjacency matrices, they can exhibit Euclidean-like spatial structure. Based on this distinction, we hypothesize that CNNs may outperform GNNs when working with spatially-variant graphs, while GNNs may excel on spatially-invariant graphs. To test this hypothesis, we compared the performance of CNNs and GNNs under two scenarios: (i) graphs in the training and test sets had the same connectivity pattern and spatial structure, and (ii) graphs in the training and test sets had the same connectivity pattern but different spatial structures. Our results confirmed that the presence of spatial structure in a graph allows for the effective use of CNNs, which may even outperform GNNs. Thus, our study contributes to the understanding of the effect of spatial graph structure on the performance of machine learning methods and allows for the selection of an appropriate algorithm based on the spatial properties of the real-life graph dataset.

Suggested Citation

  • Anna Boronina & Vladimir Maksimenko & Alexander E. Hramov, 2023. "Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data," Mathematics, MDPI, vol. 11(11), pages 1-13, May.
  • Handle: RePEc:gam:jmathe:v:11:y:2023:i:11:p:2515-:d:1159700
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/11/2515/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/11/11/2515/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Pitsik, Elena N. & Maximenko, Vladimir A. & Kurkin, Semen A. & Sergeev, Alexander P. & Stoyanov, Drozdstoy & Paunova, Rositsa & Kandilarova, Sevdalina & Simeonova, Denitsa & Hramov, Alexander E., 2023. "The topology of fMRI-based networks defines the performance of a graph neural network for the classification of patients with major depressive disorder," Chaos, Solitons & Fractals, Elsevier, vol. 167(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Oleg E. Karpov & Elena N. Pitsik & Semen A. Kurkin & Vladimir A. Maksimenko & Alexander V. Gusev & Natali N. Shusharina & Alexander E. Hramov, 2023. "Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach," IJERPH, MDPI, vol. 20(7), pages 1-17, March.
    2. Alharbi, Njud S. & Bekiros, Stelios & Jahanshahi, Hadi & Mou, Jun & Yao, Qijia, 2024. "Spatiotemporal wavelet-domain neuroimaging of chaotic EEG seizure signals in epilepsy diagnosis and prognosis with the use of graph convolutional LSTM networks," Chaos, Solitons & Fractals, Elsevier, vol. 181(C).
    3. Guo, Lei & Liu, Chengjun & Wu, Youxi & Xu, Guizhi, 2023. "fMRI-based spiking neural network verified by anti-damage capabilities under random attacks," Chaos, Solitons & Fractals, Elsevier, vol. 176(C).
    4. Ben-Loghfyry, Anouar & Charkaoui, Abderrahim, 2023. "Regularized Perona & Malik model involving Caputo time-fractional derivative with application to image denoising," Chaos, Solitons & Fractals, Elsevier, vol. 175(P1).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:11:p:2515-:d:1159700. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.