Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification
Graph Neural Networks (GNNs) have witnessed great advancement in the field of neural networks for processing graph datasets. Graph Convolutional Networks (GCNs) have outperformed current models/algorithms in accomplishing tasks such as semi-supervised node classification, link prediction, and graph...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/2/847 |
| _version_ | 1797446676287324160 |
|---|---|
| author | Atul Kumar Verma Rahul Saxena Mahipal Jadeja Vikrant Bhateja Jerry Chun-Wei Lin |
| author_facet | Atul Kumar Verma Rahul Saxena Mahipal Jadeja Vikrant Bhateja Jerry Chun-Wei Lin |
| author_sort | Atul Kumar Verma |
| collection | DOAJ |
| description | Graph Neural Networks (GNNs) have witnessed great advancement in the field of neural networks for processing graph datasets. Graph Convolutional Networks (GCNs) have outperformed current models/algorithms in accomplishing tasks such as semi-supervised node classification, link prediction, and graph classification. GCNs perform well even with a very small training dataset. The GCN framework has evolved to Graph Attention Model (GAT), GraphSAGE, and other hybrid frameworks. In this paper, we effectively usd the network centrality approach to select nodes from the training set (instead of a traditional random selection), which is fed into GCN (and GAT) to perform semi-supervised node classification tasks. This allows us to take advantage of the best positional nodes in the network. Based on empirical analysis, we choose the betweenness centrality measure for selecting the training nodes. We also mathematically justify why our proposed technique offers better training. This novel training technique is used to analyze the performance of GCN and GAT models on five benchmark networks—Cora, Citeseer, PubMed, Wiki-CS, and Amazon Computers. In GAT implementations, we obtain improved classification accuracy compared to the other state-of-the-art GCN-based methods. Moreover, to the best of our knowledge, the results obtained for Citeseer, Wiki- CS, and Amazon Computer datasets are the best compared to all the existing node classification methods. |
| first_indexed | 2024-03-09T13:44:01Z |
| format | Article |
| id | doaj.art-30200d17b58447219fa2f02dc570109b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:44:01Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-30200d17b58447219fa2f02dc570109b2023-11-30T21:02:21ZengMDPI AGApplied Sciences2076-34172023-01-0113284710.3390/app13020847Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node ClassificationAtul Kumar Verma0Rahul Saxena1Mahipal Jadeja2Vikrant Bhateja3Jerry Chun-Wei Lin4Department of Computer Science and Engineering, Malaviya National Institute of Technology Jaipur, Jaipur 302017, Rajasthan, IndiaDepartment of Computer Science and Engineering, Malaviya National Institute of Technology Jaipur, Jaipur 302017, Rajasthan, IndiaDepartment of Computer Science and Engineering, Malaviya National Institute of Technology Jaipur, Jaipur 302017, Rajasthan, IndiaDepartment of Electronics Engineering, Veer Bahadur Singh Purvanchal University, Shahganj Road, Jaunpur 222003, Uttar Pradesh, IndiaDepartment of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, 5063 Bergen, NorwayGraph Neural Networks (GNNs) have witnessed great advancement in the field of neural networks for processing graph datasets. Graph Convolutional Networks (GCNs) have outperformed current models/algorithms in accomplishing tasks such as semi-supervised node classification, link prediction, and graph classification. GCNs perform well even with a very small training dataset. The GCN framework has evolved to Graph Attention Model (GAT), GraphSAGE, and other hybrid frameworks. In this paper, we effectively usd the network centrality approach to select nodes from the training set (instead of a traditional random selection), which is fed into GCN (and GAT) to perform semi-supervised node classification tasks. This allows us to take advantage of the best positional nodes in the network. Based on empirical analysis, we choose the betweenness centrality measure for selecting the training nodes. We also mathematically justify why our proposed technique offers better training. This novel training technique is used to analyze the performance of GCN and GAT models on five benchmark networks—Cora, Citeseer, PubMed, Wiki-CS, and Amazon Computers. In GAT implementations, we obtain improved classification accuracy compared to the other state-of-the-art GCN-based methods. Moreover, to the best of our knowledge, the results obtained for Citeseer, Wiki- CS, and Amazon Computer datasets are the best compared to all the existing node classification methods.https://www.mdpi.com/2076-3417/13/2/847graph convolution network (GCN)graph attention network (GAT)network centralitysemi-supervised node classification |
| spellingShingle | Atul Kumar Verma Rahul Saxena Mahipal Jadeja Vikrant Bhateja Jerry Chun-Wei Lin Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification Applied Sciences graph convolution network (GCN) graph attention network (GAT) network centrality semi-supervised node classification |
| title | Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification |
| title_full | Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification |
| title_fullStr | Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification |
| title_full_unstemmed | Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification |
| title_short | Bet-GAT: An Efficient Centrality-Based Graph Attention Model for Semi-Supervised Node Classification |
| title_sort | bet gat an efficient centrality based graph attention model for semi supervised node classification |
| topic | graph convolution network (GCN) graph attention network (GAT) network centrality semi-supervised node classification |
| url | https://www.mdpi.com/2076-3417/13/2/847 |
| work_keys_str_mv | AT atulkumarverma betgatanefficientcentralitybasedgraphattentionmodelforsemisupervisednodeclassification AT rahulsaxena betgatanefficientcentralitybasedgraphattentionmodelforsemisupervisednodeclassification AT mahipaljadeja betgatanefficientcentralitybasedgraphattentionmodelforsemisupervisednodeclassification AT vikrantbhateja betgatanefficientcentralitybasedgraphattentionmodelforsemisupervisednodeclassification AT jerrychunweilin betgatanefficientcentralitybasedgraphattentionmodelforsemisupervisednodeclassification |