收藏切换
Element Separation and Holistic Attention Based Graph Convolutional Network Framework
收藏切换
Chuanzhen Zhu, Xuan Wang, Qiang Zheng*
Journal of Computer Research and Development | 2024, 61(8) : 2008 - 2019
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(8): 2008-2019
• Special Issue on Graph Machine Learning •
Element Separation and Holistic Attention Based Graph Convolutional Network Framework
Full
Chuanzhen Zhu, Xuan Wang, Qiang Zheng*
Affiliations
  • School of Computer and Control Engineering, Yantai University, Yantai, Shandong 264005
  • born in 1999. Master candidate. His main research interests include deep learning, brain networks, and graph neural networks

    born in 1991. PhD, associate professor. Her main research interests include image processing, machine learning, and pattern recognition

    born in 1986. PhD, professor. His main research interests include medical image processing, data mining, and artificial intelligence

About Author:

born in 1999. Master candidate. His main research interests include deep learning, brain networks, and graph neural networks

born in 1991. PhD, associate professor. Her main research interests include image processing, machine learning, and pattern recognition

born in 1986. PhD, professor. His main research interests include medical image processing, data mining, and artificial intelligence

Published: 2024-08-01 doi: 10.7544/issn1000-1239.202440143
Outline
收藏切换

Currently, graph convolutional network (GCN) holds significant potential in processing graph data and other unstructured data. However, GCN faces challenges when dealing with densely connected graphs, as their node-based neighborhood information aggregation mechanism can lead to excessive smoothing, thereby weakening the expressive power of the network graph. The construction of sparse graphs can alleviate the phenomenon of excessive smoothing during the convolution process to some extent, but sparse graphs are prone to information loss and the sparsification process lacks unified standards, affecting the model’s consistency and interpretability. To address this, we propose element separation and holistic attention graph convolutional network framework (EH-GCN). This framework does not require the basis of sparse graphs and can learn the connectivity and node features of densely connected graphs separately. Moreover, it employs a global attention mechanism to integrate connectivity and node features, thus overcoming the limitations of traditional GCN frameworks in handling densely connected graphs and enhancing the feature expression capability of the network graph. We firstly construct fully connected brain networks on three brain imaging datasets: ADNI, ABIDE, and AIBL, verifying the effectiveness of the EH-GCN model in classifying densely connected graphs. Subsequently, the model is tested on the FRANKENSTEIN chemical molecular graph dataset, demonstrating its robust generalization capability. Additionally, the interpretability analysis of the framework aligns with previous neuropathological research, further substantiating the biological basis of the framework.

graph convolutional network  /  brain network  /  graph classification  /  Alzheimer’s disease  /  Autism spectrum disorder
祝传振, 王璇, 郑强. 基于元素分离与整体注意力的图卷积网络框架. 计算机研究与发展, 2024 , 61 (8) : 2008 -2019 . DOI: 10.7544/issn1000-1239.202440143
Chuanzhen Zhu, Xuan Wang, Qiang Zheng. Element Separation and Holistic Attention Based Graph Convolutional Network Framework[J]. Journal of Computer Research and Development, 2024 , 61 (8) : 2008 -2019 . DOI: 10.7544/issn1000-1239.202440143
Year 2024 volume 61 Issue 8
85
38
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202440143
  • Receive Date:2024-03-01
  • Online Date:2026-11-17
  • Published:2024-08-01
Article Data
Affiliations
History
  • Received:2024-03-01
  • Revised:2024-05-14
Affiliations
    School of Computer and Control Engineering, Yantai University, Yantai, Shandong 264005
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440143
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