HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion
Heterogeneous Graph Neural Networks (HGNNs) have attracted significant research attention in recent years due to their ability to capture complex interactions among various node types in heterogeneous graphs (HGs). However, existing methods face critical challenges, including the loss of graph attri...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10804165/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536172532170752 |
|---|---|
| author | Yufei Zhao Hua Liu Hua Duan |
| author_facet | Yufei Zhao Hua Liu Hua Duan |
| author_sort | Yufei Zhao |
| collection | DOAJ |
| description | Heterogeneous Graph Neural Networks (HGNNs) have attracted significant research attention in recent years due to their ability to capture complex interactions among various node types in heterogeneous graphs (HGs). However, existing methods face critical challenges, including the loss of graph attribute information caused by excessive emphasis on semantic information and the difficulty of effectively integrating graph attributes with semantic information. To address these issues, this paper proposes HGNN-GAMS: a Heterogeneous Graph Neural Network for Graph Attribute Mining and Semantic Fusion. The model comprises two main components: graph attribute fusion and semantic aggregation. The graph attribute fusion module captures two intrinsic features of HGs—their unique topological structures and node attributes. The semantic aggregation module, leveraging an attention mechanism, integrates diverse semantic information within HGs. Ultimately, HGNN-GAMS fuses graph attribute features and semantic features to produce the final feature representation. This work pioneers the integration of graph attributes with semantic information and validates the model’s effectiveness through extensive experiments on real-world datasets. |
| format | Article |
| id | doaj-art-52b7883e0c2948cf998db91c4d0d8e18 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-52b7883e0c2948cf998db91c4d0d8e182025-01-15T00:01:59ZengIEEEIEEE Access2169-35362024-01-011219160319161110.1109/ACCESS.2024.351877710804165HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic FusionYufei Zhao0https://orcid.org/0009-0005-3602-8296Hua Liu1Hua Duan2https://orcid.org/0000-0002-0947-2704College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, Shandong, ChinaCollege of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, Shandong, ChinaCollege of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, Shandong, ChinaHeterogeneous Graph Neural Networks (HGNNs) have attracted significant research attention in recent years due to their ability to capture complex interactions among various node types in heterogeneous graphs (HGs). However, existing methods face critical challenges, including the loss of graph attribute information caused by excessive emphasis on semantic information and the difficulty of effectively integrating graph attributes with semantic information. To address these issues, this paper proposes HGNN-GAMS: a Heterogeneous Graph Neural Network for Graph Attribute Mining and Semantic Fusion. The model comprises two main components: graph attribute fusion and semantic aggregation. The graph attribute fusion module captures two intrinsic features of HGs—their unique topological structures and node attributes. The semantic aggregation module, leveraging an attention mechanism, integrates diverse semantic information within HGs. Ultimately, HGNN-GAMS fuses graph attribute features and semantic features to produce the final feature representation. This work pioneers the integration of graph attributes with semantic information and validates the model’s effectiveness through extensive experiments on real-world datasets.https://ieeexplore.ieee.org/document/10804165/Graph embeddingneural networksheterogeneous graphsgraph representation learning |
| spellingShingle | Yufei Zhao Hua Liu Hua Duan HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion IEEE Access Graph embedding neural networks heterogeneous graphs graph representation learning |
| title | HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion |
| title_full | HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion |
| title_fullStr | HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion |
| title_full_unstemmed | HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion |
| title_short | HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion |
| title_sort | hgnn gams heterogeneous graph neural networks for graph attribute mining and semantic fusion |
| topic | Graph embedding neural networks heterogeneous graphs graph representation learning |
| url | https://ieeexplore.ieee.org/document/10804165/ |
| work_keys_str_mv | AT yufeizhao hgnngamsheterogeneousgraphneuralnetworksforgraphattributeminingandsemanticfusion AT hualiu hgnngamsheterogeneousgraphneuralnetworksforgraphattributeminingandsemanticfusion AT huaduan hgnngamsheterogeneousgraphneuralnetworksforgraphattributeminingandsemanticfusion |