Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion
In recent years, Graph Neural Networks (GNNs) have achieved significant success in graph-based tasks. However, they still face challenges in complex scenarios, particularly in integrating local and global information, enhancing robustness to noise, and overcoming the rigidity of graph structures. To...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10849571/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576758172352512 |
|---|---|
| author | Junwen Lu Lingrui Zheng Xianmei Hua Yankun Wang |
| author_facet | Junwen Lu Lingrui Zheng Xianmei Hua Yankun Wang |
| author_sort | Junwen Lu |
| collection | DOAJ |
| description | In recent years, Graph Neural Networks (GNNs) have achieved significant success in graph-based tasks. However, they still face challenges in complex scenarios, particularly in integrating local and global information, enhancing robustness to noise, and overcoming the rigidity of graph structures. To address these issues, we propose a new GNN algorithm, LEGNN (Local and Global Enhanced Graph Neural Network), which introduces several key improvements over traditional GNN models such as GraphSAGE and GCN:Firstly, LEGNN combines a hybrid convolution method of spatial and spectral convolutions, enabling it to simultaneously capture local neighborhood relationships and global topological structures. This fusion mechanism effectively enhances the model’s ability to learn node representations, especially in complex graph structures, with accuracy improvements of 1%-2% compared to GCN and GraphSAGE. Secondly, LEGNN incorporates a noise prediction mechanism that injects controlled perturbations into the node representations, improving the model’s robustness, reducing overfitting, and enhancing generalization to unseen data. Finally, LEGNN introduces an adaptive graph structure adjustment mechanism, allowing the model to dynamically adjust the graph topology based on input data, enabling it to flexibly handle evolving data scenarios. In experiments on OGB datasets, LEGNN reduces training time by 55%-88% compared to GCN and GraphSAGE, and demonstrates higher stability when handling large-scale graph data. We validated the effectiveness of LEGNN through experiments on two OGB datasets, and the results show that LEGNN outperforms traditional GNN models in graph learning tasks, highlighting its potential in advancing the field. |
| format | Article |
| id | doaj-art-5cfb277a31fd4a3b92975fb39aba0ac9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5cfb277a31fd4a3b92975fb39aba0ac92025-01-31T00:00:54ZengIEEEIEEE Access2169-35362025-01-0113167871679910.1109/ACCESS.2025.353280610849571Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain FusionJunwen Lu0https://orcid.org/0000-0002-7098-2789Lingrui Zheng1https://orcid.org/0009-0004-0181-0774Xianmei Hua2Yankun Wang3School of Computer and Information and Engineering, Xiamen University of Technology, Xiamen, ChinaSchool of Computer and Information and Engineering, Xiamen University of Technology, Xiamen, ChinaSchool of Data and Computer Science, Xiamen Institute of Technology, Xiamen, ChinaEastern Michigan Joint College of Engineering, Beibu Gulf University, Beihai, ChinaIn recent years, Graph Neural Networks (GNNs) have achieved significant success in graph-based tasks. However, they still face challenges in complex scenarios, particularly in integrating local and global information, enhancing robustness to noise, and overcoming the rigidity of graph structures. To address these issues, we propose a new GNN algorithm, LEGNN (Local and Global Enhanced Graph Neural Network), which introduces several key improvements over traditional GNN models such as GraphSAGE and GCN:Firstly, LEGNN combines a hybrid convolution method of spatial and spectral convolutions, enabling it to simultaneously capture local neighborhood relationships and global topological structures. This fusion mechanism effectively enhances the model’s ability to learn node representations, especially in complex graph structures, with accuracy improvements of 1%-2% compared to GCN and GraphSAGE. Secondly, LEGNN incorporates a noise prediction mechanism that injects controlled perturbations into the node representations, improving the model’s robustness, reducing overfitting, and enhancing generalization to unseen data. Finally, LEGNN introduces an adaptive graph structure adjustment mechanism, allowing the model to dynamically adjust the graph topology based on input data, enabling it to flexibly handle evolving data scenarios. In experiments on OGB datasets, LEGNN reduces training time by 55%-88% compared to GCN and GraphSAGE, and demonstrates higher stability when handling large-scale graph data. We validated the effectiveness of LEGNN through experiments on two OGB datasets, and the results show that LEGNN outperforms traditional GNN models in graph learning tasks, highlighting its potential in advancing the field.https://ieeexplore.ieee.org/document/10849571/Dynamic graph structurefeature fusiongraph neural networks |
| spellingShingle | Junwen Lu Lingrui Zheng Xianmei Hua Yankun Wang Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion IEEE Access Dynamic graph structure feature fusion graph neural networks |
| title | Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion |
| title_full | Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion |
| title_fullStr | Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion |
| title_full_unstemmed | Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion |
| title_short | Graph Convolution for Large-Scale Graph Node Classification Task Based on Spatial and Frequency Domain Fusion |
| title_sort | graph convolution for large scale graph node classification task based on spatial and frequency domain fusion |
| topic | Dynamic graph structure feature fusion graph neural networks |
| url | https://ieeexplore.ieee.org/document/10849571/ |
| work_keys_str_mv | AT junwenlu graphconvolutionforlargescalegraphnodeclassificationtaskbasedonspatialandfrequencydomainfusion AT lingruizheng graphconvolutionforlargescalegraphnodeclassificationtaskbasedonspatialandfrequencydomainfusion AT xianmeihua graphconvolutionforlargescalegraphnodeclassificationtaskbasedonspatialandfrequencydomainfusion AT yankunwang graphconvolutionforlargescalegraphnodeclassificationtaskbasedonspatialandfrequencydomainfusion |