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
  • [31] GRAPH RECOGNITION BY NEURAL NETWORKS
    DREYFUS, G
    ZIPPELIUS, A
    NEURAL NETWORKS FROM MODELS TO APPLICATIONS, 1989, : 483 - 492
  • [32] STOCHASTIC GRAPH NEURAL NETWORKS
    Gao, Zhan
    Isufi, Elvin
    Ribeiro, Alejandro
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 9080 - 9084
  • [33] Introduction to Graph Neural Networks
    Liu Z.
    Zhou J.
    1600, Morgan and Claypool Publishers (14): : 1 - 127
  • [34] Neural networks and graph theory
    Xu, J
    Bao, Z
    SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2002, 45 (01): : 1 - 24
  • [35] ConveXplainer for Graph Neural Networks
    Pereira, Tamara A.
    Nascimento, Erik Jhones F.
    Mesquita, Diego
    Souza, Amauri H.
    INTELLIGENT SYSTEMS, PT II, 2022, 13654 : 588 - 600
  • [36] Graph Neural Networks with Heterophily
    Zhu, Jiong
    Rossi, Ryan A.
    Rao, Anup
    Mai, Tung
    Lipka, Nedim
    Ahmed, Nesreen K.
    Koutra, Danai
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 11168 - 11176
  • [37] Binary Graph Neural Networks
    Bahri, Mehdi
    Bahl, Gaetan
    Zafeiriou, Stefanos
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 9487 - 9496
  • [38] Polarized Graph Neural Networks
    Fang, Zheng
    Xu, Lingjun
    Song, Guojie
    Long, Qingqing
    Zhang, Yingxue
    PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, : 1404 - 1413
  • [39] Convolutional Graph Neural Networks
    Gama, Fernando
    Marques, Antonio G.
    Leus, Geert
    Ribeiro, Alejandro
    CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 452 - 456
  • [40] Streaming Graph Neural Networks
    Ma, Yao
    Guo, Ziyi
    Ren, Zhaochun
    Tang, Jiliang
    Yin, Dawei
    PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 719 - 728