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
  • [41] Graph Neural Networks in TensorFlow
    Perozzi, Bryan
    Abu-El-Haija, Sami
    Tsitsulin, Anton
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 5786 - 5787
  • [42] Neural networks and graph theory
    许进
    保铮
    Science in China(Series F:Information Sciences), 2002, (01) : 1 - 24
  • [43] Hyperbolic Graph Neural Networks
    Liu, Qi
    Nickel, Maximilian
    Kiela, Douwe
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [44] Neural networks and graph theory
    Jin Xu
    Zheng Bao
    Science in China Series F: Information Sciences, 2002, 45 (1): : 1 - 24
  • [45] Orthogonal Graph Neural Networks
    Guo, Kai
    Zhou, Kaixiong
    Hu, Xia
    Li, Yu
    Chang, Yi
    Wang, Xin
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 3996 - 4004
  • [46] Clenshaw Graph Neural Networks
    Guo, Yuhe
    Wei, Zhewei
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 614 - 625
  • [47] Schatten Graph Neural Networks
    Liu, Youfa
    Chen, Yongyong
    Chen, Guo
    Zhang, Jiawei
    IEEE ACCESS, 2022, 10 : 56482 - 56492
  • [48] AGGREGATION GRAPH NEURAL NETWORKS
    Gama, Fernando
    Marques, Antonio G.
    Ribeiro, Alejandro
    Leus, Geert
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 4943 - 4947
  • [49] Survey on Graph Neural Networks
    Gkarmpounis, Georgios
    Vranis, Christos
    Vretos, Nicholas
    Daras, Petros
    IEEE ACCESS, 2024, 12 : 128816 - 128832
  • [50] Implicit Graph Neural Networks
    Gu, Fangda
    Chang, Heng
    Zhu, Wenwu
    Sojoudi, Somayeh
    El Ghaoui, Laurent
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33