Graph isomorphisms effect structure optimization of neural networks

被引：1
|
作者：
Igel, C [1 ]
Stagge, P [1 ]
机构：
[1] Ruhr Univ Bochum, Inst Neuroinformat, D-44780 Bochum, Germany
来源：
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词：
D O I：
10.1109/IJCNN.2002.1005459
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Concepts from graph theory and molecular evolution are proposed for analyzing effects of redundancy induced by graph isomorphisms on structure optimization of neural networks. It is demonstrated that a graph database that considers isomorphisms can drastically reduce the number of evaluations in an evolutionary structure optimization process.
引用
收藏
页码：142 / 147
页数：4
相关论文
共 50 条
  • [1] Learning to Count Isomorphisms with Graph Neural Networks
    Yu, Xingtong
    Liu, Zemin
    Fang, Yuan
    Zhang, Xinming
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4845 - 4853
  • [2] Structure optimization and isomorphisms
    Stagge, P
    Igel, C
    THEORETICAL ASPECTS OF EVOLUTIONARY COMPUTING, 2001, : 409 - 422
  • [3] Graph Structure Estimation Neural Networks
    Wang, Ruijia
    Mou, Shuai
    Wang, Xiao
    Xiao, Wanpeng
    Ju, Qi
    Shi, Chuan
    Xie, Xing
    PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021), 2021, : 342 - 353
  • [4] Graph Structure Learning for Robust Graph Neural Networks
    Jin, Wei
    Ma, Yao
    Liu, Xiaorui
    Tang, Xianfeng
    Wang, Suhang
    Tang, Jiliang
    KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 66 - 74
  • [5] Heterogeneous Graph Structure Learning for Graph Neural Networks
    Zhao, Jianan
    Wang, Xiao
    Shi, Chuan
    Hu, Binbin
    Song, Guojie
    Ye, Yanfang
    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 : 4697 - 4705
  • [6] Graph neural networks for deep portfolio optimization
    Ekmekcioglu, Omer
    Pinar, Mustafa C.
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (28): : 20663 - 20674
  • [7] Graph neural networks for deep portfolio optimization
    Ömer Ekmekcioğlu
    Mustafa Ç. Pınar
    Neural Computing and Applications, 2023, 35 : 20663 - 20674
  • [8] Combinatorial Optimization and Reasoning with Graph Neural Networks
    Cappart, Quentin
    Chetelat, Didier
    Khalil, Elias B.
    Lodi, Andrea
    Morris, Christopher
    Velickovic, Petar
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4348 - 4355
  • [9] Combinatorial Optimization and Reasoning with Graph Neural Networks
    Cappart, Quentin
    Chetelat, Didier
    Khalil, Elias B.
    Lodi, Andrea
    Morris, Christopher
    Velickovic, Petar
    JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
  • [10] Graph structure and homophily for label propagation in Graph Neural Networks
    Vandromme, Maxence
    Petiton, Serge G.
    2023 IEEE 16TH INTERNATIONAL SYMPOSIUM ON EMBEDDED MULTICORE/MANY-CORE SYSTEMS-ON-CHIP, MCSOC, 2023, : 194 - 201
12345