收藏切换
HSEGRL: A Hierarchical Self-Explainable Graph Representation Learning Model
收藏切换
Ping Li1, 2, Shuhan Song1, 2, Yuan Zhang1, 2, Huawei Cao1, 3, *, Xiaochun Ye1, Zhimin Tang1
Journal of Computer Research and Development | 2024, 61(8) : 1993 - 2007
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(8): 1993-2007
• Special Issue on Graph Machine Learning •
HSEGRL: A Hierarchical Self-Explainable Graph Representation Learning Model
Full
Ping Li1, 2, Shuhan Song1, 2, Yuan Zhang1, 2, Huawei Cao1, 3, *, Xiaochun Ye1, Zhimin Tang1
Affiliations
  • 1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
  • 2University of Chinese Academy of Sciences, Beijing 100049
  • 3University of Chinese Academy of Sciences, Nanjing 211135
  • born in 1995. PhD candidate. Student member of CCF. Her main research interest includes the optimization of graph neural network models and the explainability

    born in 1997. PhD candidate. Student member of CCF. His main research interests include graph neural networks, graph self-supervised learning, and graph neural network architecture search and robustness on graph learning. ()

    born in 1990. PhD candidate. Member of CCF. Her main research interests include graph processing and parallel computing. ()

    born in 1989. PhD, associate professor. Member of CCF. His main research interests include parallel computing and high throughput computing architecture

    born in 1981. PhD, professor. Member of CCF. His main research interests include algorithm paralleling and optimizing, software simulation, and architecture for high throughput computer. ()

    born in 1966. PhD, professor. Senior member of CCF. His main research interests include high performance computer architecture, processor design, and digital signal processing. ()

About Author:

born in 1995. PhD candidate. Student member of CCF. Her main research interest includes the optimization of graph neural network models and the explainability

born in 1997. PhD candidate. Student member of CCF. His main research interests include graph neural networks, graph self-supervised learning, and graph neural network architecture search and robustness on graph learning. ()

born in 1990. PhD candidate. Member of CCF. Her main research interests include graph processing and parallel computing. ()

born in 1989. PhD, associate professor. Member of CCF. His main research interests include parallel computing and high throughput computing architecture

born in 1981. PhD, professor. Member of CCF. His main research interests include algorithm paralleling and optimizing, software simulation, and architecture for high throughput computer. ()

born in 1966. PhD, professor. Senior member of CCF. His main research interests include high performance computer architecture, processor design, and digital signal processing. ()

Published: 2024-08-01 doi: 10.7544/issn1000-1239.202440142
Outline
收藏切换

In recent years, with the extensive application of graph neural network (GNN) technology in the fields such as social network, information, chemistry and biology, the interpretability of GNN has attracted widespread attention. However, prevailing explanation methods fail to capture the hierarchical explanation information, and these hierarchical information has not been fully utilized to improve the classification accuracy of graph tasks. To address this issue, we propose a hierarchical self-explanation graph representation learning model called HSEGRL (hierarchical self-explanation graph representation learning). This model, by discovering hierarchical information in the graph structure, predicts graph classifications while outputting hierarchical self-explanation results. Specifically, we design the basic unit for extracting hierarchical information—interpreters. These interpreters consist of an encoder that extracts node features, a pooling layer that perceives hierarchical explanation-aware subgraphs, and a decoder that refines higher-order explanation information. We refine the pooling mechanism with an explanation-aware strategy, enabling the hierarchical selection of subgraphs based on the evaluation of the model’s topology and feature importance, thereby facilitating hierarchical self-explanation in conjunction with graph classification. HSEGRL is a functionally comprehensive and transferable self-explanatory graph representation learning framework that can hierarchically consider the model’s topological information and node feature information. We conduct extensive experiments on datasets from molecular, protein, and social network, and demonstrate that HSEGRL surpasses existing advanced self-explanatory graph neural network models and graph neural network models in terms of graph classification performance. Furthermore, the visualization of layered explanation outcomes substantiates the credibility of our proposed explanation methodology.

graph representation learning  /  graph neural networks  /  self-explainable model  /  graph topology  /  message passing mechanism
李平, 宋舒寒, 张园, 曹华伟, 叶笑春, 唐志敏. HSEGRL:一种分层可自解释的图表示学习模型. 计算机研究与发展, 2024 , 61 (8) : 1993 -2007 . DOI: 10.7544/issn1000-1239.202440142
Ping Li, Shuhan Song, Yuan Zhang, Huawei Cao, Xiaochun Ye, Zhimin Tang. HSEGRL: A Hierarchical Self-Explainable Graph Representation Learning Model[J]. Journal of Computer Research and Development, 2024 , 61 (8) : 1993 -2007 . DOI: 10.7544/issn1000-1239.202440142
Year 2024 volume 61 Issue 8
84
43
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202440142
  • Receive Date:2024-03-15
  • Online Date:2026-11-17
  • Published:2024-08-01
Article Data
Affiliations
History
  • Received:2024-03-15
  • Revised:2024-05-20
Affiliations
    1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
    2University of Chinese Academy of Sciences, Beijing 100049
    3University of Chinese Academy of Sciences, Nanjing 211135
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440142
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