收藏切换
Graph Classification Method Based on Graph Kernel Isomorphism Network
收藏切换
Lixiang Xu1, Wei Ge1, Enhong Chen2, *, Bin Luo3
Journal of Computer Research and Development | 2024, 61(4) : 903 - 915
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(4): 903-915
• Artificial Intelligence •
Graph Classification Method Based on Graph Kernel Isomorphism Network
Full
Lixiang Xu1, Wei Ge1, Enhong Chen2, *, Bin Luo3
Affiliations
  • 1School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601
  • 2Anhui Province Key Laboratory of Big Data Analysis and Application(School of Computer Science and Technology, University of Science and Technology of China), Hefei 230027
  • 3School of Computer Science and Technology, Anhui University, Hefei 230601
  • born in 1981. PhD, professor. His research interests include machine learning, data mining, and personalized recommendation system

    born in 1996. Master candidate. His interests include graph neural network and graph representation learning

    born in 1968. PhD, professor. His research interests include data mining, education big data analysis, and personalized recommendation system

    born in 1963. PhD, professor. His research interests include pattern recognition, machine learning and data mining

About Author:

born in 1981. PhD, professor. His research interests include machine learning, data mining, and personalized recommendation system

born in 1996. Master candidate. His interests include graph neural network and graph representation learning

born in 1968. PhD, professor. His research interests include data mining, education big data analysis, and personalized recommendation system

born in 1963. PhD, professor. His research interests include pattern recognition, machine learning and data mining

Published: 2024-04-01 doi: 10.7544/issn1000-1239.202221004
Outline
收藏切换

Graph representation learning has become a research hotspot in the field of graph deep learning. Most graph neural networks suffer from oversmoothing, and these methods focus on graph node features and pay little attention to the structural features of graphs. In order to improve the representation of graph structural features, we propose a graph classification method based on graph kernel homomorphic network, namely KerGIN. The method first encodes the node features of the graph through graph isomorphism network(GIN), and then uses the graph kernel method to encode the graph structure. The Nyström method is further used to reduce the dimension of the graph kernel matrix. The graph kernel matrix is aligned with the graph feature matrix with the help of MLP, and the feature encoding and structure encoding of the graph are adaptively weighted and fused through the attention mechanism to obtain the final feature representation of the graph, which enhances the ability to express the structural feature information of the graph. Finally, the model is experimentally evaluated on seven publicly available graph classification datasets: compared with the existing graph representation models, KerGIN model is able to improve the graph classification accuracy substantially, and it can enhance the ability of GIN to represent the graph structural feature information.

graph classification  /  graph neural network  /  graph kernel  /  Nyström method  /  graph attention mechanism
徐立祥, 葛伟, 陈恩红, 罗斌. 基于图核同构网络的图分类方法. 计算机研究与发展, 2024 , 61 (4) : 903 -915 . DOI: 10.7544/issn1000-1239.202221004
Lixiang Xu, Wei Ge, Enhong Chen, Bin Luo. Graph Classification Method Based on Graph Kernel Isomorphism Network[J]. Journal of Computer Research and Development, 2024 , 61 (4) : 903 -915 . DOI: 10.7544/issn1000-1239.202221004
Year 2024 volume 61 Issue 4
96
48
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202221004
  • Receive Date:2022-12-07
  • Online Date:2026-11-17
  • Published:2024-04-01
Article Data
Affiliations
History
  • Received:2022-12-07
  • Revised:2023-06-05
Affiliations
    1School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601
    2Anhui Province Key Laboratory of Big Data Analysis and Application(School of Computer Science and Technology, University of Science and Technology of China), Hefei 230027
    3School of Computer Science and Technology, Anhui University, Hefei 230601
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202221004
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT