IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i8p1300-d793586.html
   My bibliography  Save this article

Robust Graph Neural Networks via Ensemble Learning

Author

Listed:
  • Qi Lin

    (School of Software, Dalian University of Technology, Dalian 116620, China)

  • Shuo Yu

    (School of Software, Dalian University of Technology, Dalian 116620, China)

  • Ke Sun

    (School of Software, Dalian University of Technology, Dalian 116620, China)

  • Wenhong Zhao

    (Ultraprecision Machining Center, Zhejiang University of Technology, Hangzhou 310014, China)

  • Osama Alfarraj

    (Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia)

  • Amr Tolba

    (Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia)

  • Feng Xia

    (School of Engineering, IT and Physical Sciences, Federation University Australia, Ballarat, VIC 3353, Australia)

Abstract

Graph neural networks (GNNs) have demonstrated a remarkable ability in the task of semi-supervised node classification. However, most existing GNNs suffer from the nonrobustness issues, which poses a great challenge for applying GNNs into sensitive scenarios. Some researchers concentrate on constructing an ensemble model to mitigate the nonrobustness issues. Nevertheless, these methods ignore the interaction among base models, leading to similar graph representations. Moreover, due to the deterministic propagation applied in most existing GNNs, each node highly relies on its neighbors, leaving the nodes to be sensitive to perturbations. Therefore, in this paper, we propose a novel framework of graph ensemble learning based on knowledge passing (called GEL) to address the above issues. In order to achieve interaction, we consider the predictions of prior models as knowledge to obtain more reliable predictions. Moreover, we design a multilayer DropNode propagation strategy to reduce each node’s dependence on particular neighbors. This strategy also empowers each node to aggregate information from diverse neighbors, alleviating oversmoothing issues. We conduct experiments on three benchmark datasets, including Cora, Citeseer, and Pubmed. GEL outperforms GCN by more than 5% in terms of accuracy across all three datasets and also performs better than other state-of-the-art baselines. Extensive experimental results also show that the GEL alleviates the nonrobustness and oversmoothing issues.

Suggested Citation

  • Qi Lin & Shuo Yu & Ke Sun & Wenhong Zhao & Osama Alfarraj & Amr Tolba & Feng Xia, 2022. "Robust Graph Neural Networks via Ensemble Learning," Mathematics, MDPI, vol. 10(8), pages 1-14, April.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:8:p:1300-:d:793586
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/8/1300/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/8/1300/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Christoph Stadtfeld & András Vörös & Timon Elmer & Zsófia Boda & Isabel J. Raabe, 2019. "Integration in emerging social networks explains academic failure and success," Proceedings of the National Academy of Sciences, Proceedings of the National Academy of Sciences, vol. 116(3), pages 792-797, January.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ke Sun & Shuo Yu & Ciyuan Peng & Yueru Wang & Osama Alfarraj & Amr Tolba & Feng Xia, 2022. "Relational Structure-Aware Knowledge Graph Representation in Complex Space," Mathematics, MDPI, vol. 10(11), pages 1-16, June.
    2. Kleyton da Costa, 2023. "Anomaly Detection in Global Financial Markets with Graph Neural Networks and Nonextensive Entropy," Papers 2308.02914, arXiv.org, revised Aug 2023.
    3. Jiacheng Hou & Tianhao Tao & Haoye Lu & Amiya Nayak, 2023. "Intelligent Caching with Graph Neural Network-Based Deep Reinforcement Learning on SDN-Based ICN," Future Internet, MDPI, vol. 15(8), pages 1-20, July.

    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. Rodrigo Dorantes-Gilardi & Aurora A. Ramírez-Álvarez & Diana Terrazas-Santamaría, 2021. "Is there a differentiated gender effect of collaboration with supercited authors? Evidence from early-career economists," Serie documentos de trabajo del Centro de Estudios Económicos 2021-05, El Colegio de México, Centro de Estudios Económicos.
    2. Julia M. Rohrer & Tamás Keller & Felix Elwert, 2020. "Proximity Can Induce Diverse Friendships: A Large Randomized Classroom Experiment," CERS-IE WORKING PAPERS 2053, Institute of Economics, Centre for Economic and Regional Studies.
    3. Simpson, Cohen R., 2022. "Social support and network formation in a small-scale horticulturalist population," LSE Research Online Documents on Economics 116694, London School of Economics and Political Science, LSE Library.

    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:10:y:2022:i:8:p:1300-:d:793586. 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.