Determining the optimal number of GAT and GCN layers for node classification in graph neural networks
Node classification in complex networks plays an important role including social network analysis and recommendation systems. Some graph neural networks such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) have emerged as effective approaches for achieving high-performance c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/40357/1/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN.pdf http://umpir.ump.edu.my/id/eprint/40357/2/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN%20layers%20for%20node%20classification%20in%20graph%20neural%20networks_ABS.pdf |
| _version_ | 1825815470727495680 |
|---|---|
| author | Noor, Humaira Islam, Niful Hossain Mukta, Md Saddam Nur Shazwani, Kamarudin Khan Raiaan, Mohaimenul Azam Azam, Sami |
| author_facet | Noor, Humaira Islam, Niful Hossain Mukta, Md Saddam Nur Shazwani, Kamarudin Khan Raiaan, Mohaimenul Azam Azam, Sami |
| author_sort | Noor, Humaira |
| collection | UMP |
| description | Node classification in complex networks plays an important role including social network analysis and recommendation systems. Some graph neural networks such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) have emerged as effective approaches for achieving high-performance classification in such tasks. However, constructing a graph neural network architecture is challenging particularly due to the complex task of determining the optimal number of layers. This study presents a mathematical formula for determining the optimal number of GCN and GAT hidden layers. The experiment was conducted on ten benchmark datasets, evaluating performance metrices such as accuracy, precision, recall, F1-score, and MCC for identifying the best estimation of number of hidden layers. According to the experimental findings, the number of GAT and GCN layers selected has a substantial impact on classification accuracy. Studies show that adding extra layers after the optimum number of layers has a negative or no impact on the classification performance. Our proposed approximation technique may provide valuable insights for enhancing efficiency and accuracy of the Graph Neural Network algorithms. |
| first_indexed | 2024-04-22T01:25:59Z |
| format | Conference or Workshop Item |
| id | UMPir40357 |
| institution | Universiti Malaysia Pahang |
| language | English English |
| last_indexed | 2024-04-22T01:25:59Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | UMPir403572024-04-16T04:15:42Z http://umpir.ump.edu.my/id/eprint/40357/ Determining the optimal number of GAT and GCN layers for node classification in graph neural networks Noor, Humaira Islam, Niful Hossain Mukta, Md Saddam Nur Shazwani, Kamarudin Khan Raiaan, Mohaimenul Azam Azam, Sami QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Node classification in complex networks plays an important role including social network analysis and recommendation systems. Some graph neural networks such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) have emerged as effective approaches for achieving high-performance classification in such tasks. However, constructing a graph neural network architecture is challenging particularly due to the complex task of determining the optimal number of layers. This study presents a mathematical formula for determining the optimal number of GCN and GAT hidden layers. The experiment was conducted on ten benchmark datasets, evaluating performance metrices such as accuracy, precision, recall, F1-score, and MCC for identifying the best estimation of number of hidden layers. According to the experimental findings, the number of GAT and GCN layers selected has a substantial impact on classification accuracy. Studies show that adding extra layers after the optimum number of layers has a negative or no impact on the classification performance. Our proposed approximation technique may provide valuable insights for enhancing efficiency and accuracy of the Graph Neural Network algorithms. Institute of Electrical and Electronics Engineers Inc. 2023 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/40357/1/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN.pdf pdf en http://umpir.ump.edu.my/id/eprint/40357/2/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN%20layers%20for%20node%20classification%20in%20graph%20neural%20networks_ABS.pdf Noor, Humaira and Islam, Niful and Hossain Mukta, Md Saddam and Nur Shazwani, Kamarudin and Khan Raiaan, Mohaimenul Azam and Azam, Sami (2023) Determining the optimal number of GAT and GCN layers for node classification in graph neural networks. In: 8th International Conference on Software Engineering and Computer Systems, ICSECS 2023 , 25-27 August 2023 , Penang. pp. 111-116. (192961). ISBN 979-835031093-1 (Published) https://doi.org/10.1109/ICSECS58457.2023.10256323 |
| spellingShingle | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Noor, Humaira Islam, Niful Hossain Mukta, Md Saddam Nur Shazwani, Kamarudin Khan Raiaan, Mohaimenul Azam Azam, Sami Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title | Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title_full | Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title_fullStr | Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title_full_unstemmed | Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title_short | Determining the optimal number of GAT and GCN layers for node classification in graph neural networks |
| title_sort | determining the optimal number of gat and gcn layers for node classification in graph neural networks |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) |
| url | http://umpir.ump.edu.my/id/eprint/40357/1/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN.pdf http://umpir.ump.edu.my/id/eprint/40357/2/Determining%20the%20optimal%20number%20of%20GAT%20and%20GCN%20layers%20for%20node%20classification%20in%20graph%20neural%20networks_ABS.pdf |
| work_keys_str_mv | AT noorhumaira determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks AT islamniful determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks AT hossainmuktamdsaddam determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks AT nurshazwanikamarudin determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks AT khanraiaanmohaimenulazam determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks AT azamsami determiningtheoptimalnumberofgatandgcnlayersfornodeclassificationingraphneuralnetworks |