HAPGNN: Hop-wise attentive PageRank-Based graph neural network

Minjae Lee, Seoung Bum Kim

    Research output: Contribution to journalArticlepeer-review

    8 Citations (Scopus)

    Abstract

    With the emergence of graph neural networks (GNNs), deep learning techniques for non-Euclidean data have become the go-to method for various graph processing tasks. However, many GNNs suffer from over-smoothing, in which node features become indistinguishable with the use of multiple message passing layers and do not generalize real-world non-homogenous graph data well. To address these issues, we propose an enhanced adjustable method that attends to important hops via independent learnable weights and includes an initial connection method to further stabilize the larger model. We conducted extensive experiments on 12 real-world graph benchmark datasets of various sizes and network homophily levels to show our approach outperforms several recently proposed adaptive methods for node classification tasks.

    Original languageEnglish
    Pages (from-to)435-452
    Number of pages18
    JournalInformation Sciences
    Volume613
    DOIs
    Publication statusPublished - 2022 Oct

    Bibliographical note

    Funding Information:
    This research was supported by Brain Korea 21 FOUR, the Ministry of Science and ICT (MSIT) in Korea under the ITRC support program supervised by the IITP (IITP-2020-0-01749), and the National Research Foundation of Korea grant funded by the Korea government (RS-2022-00144190).

    Publisher Copyright:
    © 2022 Elsevier Inc.

    Keywords

    • Attention
    • Deep learning
    • Graph neural networks
    • Homophily
    • Over-smoothing

    ASJC Scopus subject areas

    • Software
    • Information Systems and Management
    • Artificial Intelligence
    • Theoretical Computer Science
    • Control and Systems Engineering
    • Computer Science Applications

    Fingerprint

    Dive into the research topics of 'HAPGNN: Hop-wise attentive PageRank-Based graph neural network'. Together they form a unique fingerprint.

    Cite this