Multi-Semantic Alignment Graph Convolutional Network
Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic A...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2022.2115010 |
| _version_ | 1797683994678001664 |
|---|---|
| author | Jisheng Qin Xiaoqin Zeng Shengli Wu Yang Zou |
| author_facet | Jisheng Qin Xiaoqin Zeng Shengli Wu Yang Zou |
| author_sort | Jisheng Qin |
| collection | DOAJ |
| description | Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines. |
| first_indexed | 2024-03-12T00:23:57Z |
| format | Article |
| id | doaj.art-480d101774f44301b4700bdb2703a4f9 |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:23:57Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-480d101774f44301b4700bdb2703a4f92023-09-15T10:48:01ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013412313233110.1080/09540091.2022.21150102115010Multi-Semantic Alignment Graph Convolutional NetworkJisheng Qin0Xiaoqin Zeng1Shengli Wu2Yang Zou3Institute of Intelligence Science and Technology, Hohai UniversityInstitute of Intelligence Science and Technology, Hohai UniversitySchool of Computing, Ulster UniversityInstitute of Intelligence Science and Technology, Hohai UniversityGraph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines.http://dx.doi.org/10.1080/09540091.2022.2115010graph convolutional networkmulti-semantic alignmentsemantic alignmentgcn |
| spellingShingle | Jisheng Qin Xiaoqin Zeng Shengli Wu Yang Zou Multi-Semantic Alignment Graph Convolutional Network Connection Science graph convolutional network multi-semantic alignment semantic alignment gcn |
| title | Multi-Semantic Alignment Graph Convolutional Network |
| title_full | Multi-Semantic Alignment Graph Convolutional Network |
| title_fullStr | Multi-Semantic Alignment Graph Convolutional Network |
| title_full_unstemmed | Multi-Semantic Alignment Graph Convolutional Network |
| title_short | Multi-Semantic Alignment Graph Convolutional Network |
| title_sort | multi semantic alignment graph convolutional network |
| topic | graph convolutional network multi-semantic alignment semantic alignment gcn |
| url | http://dx.doi.org/10.1080/09540091.2022.2115010 |
| work_keys_str_mv | AT jishengqin multisemanticalignmentgraphconvolutionalnetwork AT xiaoqinzeng multisemanticalignmentgraphconvolutionalnetwork AT shengliwu multisemanticalignmentgraphconvolutionalnetwork AT yangzou multisemanticalignmentgraphconvolutionalnetwork |