Graphon Neural Networks and the Transferability of Graph Neural Networks

被引:0
|
作者
Ruiz, Luana [1 ]
Chamon, Luiz F. O. [1 ]
Ribeiro, Alejandro [1 ]
机构
[1] Univ Penn, Dept Elect & Syst Eng, Philadelphia, PA 19143 USA
关键词
CONVERGENT SEQUENCES;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph neural networks (GNNs) rely on graph convolutions to extract local features from network data. These graph convolutions combine information from adjacent nodes using coefficients that are shared across all nodes. Since these coefficients are shared and do not depend on the graph, one can envision using the same coefficients to define a GNN on another graph. This motivates analyzing the transferability of GNNs across graphs. In this paper we introduce graphon NNs as limit objects of GNNs and prove a bound on the difference between the output of a GNN and its limit graphon-NN. This bound vanishes with growing number of nodes if the graph convolutional filters are bandlimited in the graph spectral domain. This result establishes a tradeoff between discriminability and transferability of GNNs.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Transferability of graph neural networks: An extended graphon approach
    Maskey, Sohir
    Levie, Ron
    Kutyniok, Gitta
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2023, 63 : 48 - 83
  • [2] Graphon Pooling in Graph Neural Networks
    Parada-Mayorga, Alejandro
    Ruiz, Luana
    Ribeiro, Alejandro
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 860 - 864
  • [3] Training Graph Neural Networks by Graphon Estimation
    Hu, Ziqing
    Fang, Yihao
    Lin, Lizhen
    2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2021, : 5153 - 5162
  • [4] Transferability Properties of Graph Neural Networks
    Ruiz, Luana
    Chamon, Luiz F. O.
    Ribeiro, Alejandro
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2023, 71 : 3474 - 3489
  • [5] Transferability of spectral graph convolutional neural networks
    Levie, Ron
    Huang, Wei
    Bucci, Lorenzo
    Bronstein, Michael
    Kutyniok, Gitta
    Journal of Machine Learning Research, 2021, 22
  • [6] Graph Neural Networks: Architectures, Stability, and Transferability
    Ruiz, Luana
    Gama, Fernando
    Ribeiro, Alejandro
    PROCEEDINGS OF THE IEEE, 2021, 109 (05) : 660 - 682
  • [7] Transferability of coVariance Neural Networks
    Sihag, Saurabh
    Mateos, Gonzalo
    McMillan, Corey
    Ribeiro, Alejandro
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2024, 18 (02) : 199 - 215
  • [8] On Robustness and Transferability of Convolutional Neural Networks
    Djolonga, Josip
    Yung, Jessica
    Tschannen, Michael
    Romijnders, Rob
    Beyer, Lucas
    Kolesnikov, Alexander
    Puigcerver, Joan
    Minderer, Matthias
    D'Amour, Alexander
    Moldovan, Dan
    Gelly, Sylvain
    Houlsby, Neil
    Zhai, Xiaohua
    Lucic, Mario
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 16453 - 16463
  • [9] Graph neural networks
    Corso G.
    Stark H.
    Jegelka S.
    Jaakkola T.
    Barzilay R.
    Nature Reviews Methods Primers, 4 (1):
  • [10] Graph neural networks
    不详
    NATURE REVIEWS METHODS PRIMERS, 2024, 4 (01):