Attention-based graph neural networks: a survey

被引:0
|
作者
Chengcheng Sun
Chenhao Li
Xiang Lin
Tianji Zheng
Fanrong Meng
Xiaobin Rui
Zhixiao Wang
机构
[1] China University of Mining and Technology,School of Computer Science and Technology
[2] Ministry of Education of the People’s Republic of China,Mine Digitization Engineering Research Center
来源
关键词
Graph neural networks; Attention mechanism; Graph attention networks; Graph transformers; Graph representation learning;
D O I
暂无
中图分类号
学科分类号
摘要
Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years, attention mechanism, which is brilliant in the fields of natural language processing and computer vision, is introduced to GNNs to adaptively select the discriminative features and automatically filter the noisy information. To the best of our knowledge, due to the fast-paced advances in this domain, a systematic overview of attention-based GNNs is still missing. To fill this gap, this paper aims to provide a comprehensive survey on recent advances in attention-based GNNs. Firstly, we propose a novel two-level taxonomy for attention-based GNNs from the perspective of development history and architectural perspectives. Specifically, the upper level reveals the three developmental stages of attention-based GNNs, including graph recurrent attention networks, graph attention networks, and graph transformers. The lower level focuses on various typical architectures of each stage. Secondly, we review these attention-based methods following the proposed taxonomy in detail and summarize the advantages and disadvantages of various models. A model characteristics table is also provided for a more comprehensive comparison. Thirdly, we share our thoughts on some open issues and future directions of attention-based GNNs. We hope this survey will provide researchers with an up-to-date reference regarding applications of attention-based GNNs. In addition, to cope with the rapid development in this field, we intend to share the relevant latest papers as an open resource at https://github.com/sunxiaobei/awesome-attention-based-gnns.
引用
收藏
页码:2263 / 2310
页数:47
相关论文
共 50 条
  • [1] Attention-based graph neural networks: a survey
    Sun, Chengcheng
    Li, Chenhao
    Lin, Xiang
    Zheng, Tianji
    Meng, Fanrong
    Rui, Xiaobin
    Wang, Zhixiao
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (SUPPL 2) : 2263 - 2310
  • [2] Revisiting Attention-Based Graph Neural Networks for Graph Classification
    Tao, Ye
    Li, Ying
    Wu, Zhonghai
    [J]. PARALLEL PROBLEM SOLVING FROM NATURE - PPSN XVII, PPSN 2022, PT I, 2022, 13398 : 442 - 458
  • [3] Seizure localisation with attention-based graph neural networks
    Grattarola, Daniele
    Livi, Lorenzo
    Alippi, Cesare
    Wennberg, Richard
    Valiante, Taufik A.
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2022, 203
  • [4] Demystifying Oversmoothing in Attention-Based Graph Neural Networks
    Wu, Xinyi
    Ajorlou, Amir
    Wu, Zihui
    Jadbabaie, Ali
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [5] Global Attention-Based Graph Neural Networks for Node Classification
    Chen, Jiusheng
    Fang, Chengyuan
    Zhang, Xiaoyu
    [J]. NEURAL PROCESSING LETTERS, 2023, 55 (04) : 4127 - 4150
  • [6] Global Attention-Based Graph Neural Networks for Node Classification
    Jiusheng Chen
    Chengyuan Fang
    Xiaoyu Zhang
    [J]. Neural Processing Letters, 2023, 55 : 4127 - 4150
  • [7] Infrared spectra prediction using attention-based graph neural networks
    Saquer, Naseem
    Iqbal, Razib
    Ellis, Joshua D.
    Yoshimatsu, Keiichi
    [J]. DIGITAL DISCOVERY, 2024, 3 (03): : 602 - 609
  • [8] Predicting Cardiotoxicity of Molecules Using Attention-Based Graph Neural Networks
    Vinh, Tuan
    Nguyen, Loc
    Trinh, Quang H.
    Nguyen-Vo, Thanh-Hoang
    Nguyen, Binh P.
    [J]. JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2024, 64 (06) : 1816 - 1827
  • [9] An Attention-Based Graph Neural Network for Spam Bot Detection in Social Networks
    Zhao, Chensu
    Xin, Yang
    Li, Xuefeng
    Zhu, Hongliang
    Yang, Yixian
    Chen, Yuling
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (22): : 1 - 15
  • [10] ATPGNN: Reconstruction of Neighborhood in Graph Neural Networks With Attention-Based Topological Patterns
    Wang, Kehao
    Qian, Hantao
    Zeng, Xuming
    Chen, Mozi
    Liu, Kezhong
    Zheng, Kai
    Zhou, Pan
    Wu, Dapeng
    [J]. IEEE ACCESS, 2021, 9 : 9218 - 9234