NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning
Network node embedding captures structural and relational information of nodes in the network and allows for us to use machine learning algorithms for various prediction tasks on network data that have an inherently complex and disordered structure. Network node embedding should preserve as much inf...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/2/775 |
| _version_ | 1827369870619049984 |
|---|---|
| author | Volkan Altuntas |
| author_facet | Volkan Altuntas |
| author_sort | Volkan Altuntas |
| collection | DOAJ |
| description | Network node embedding captures structural and relational information of nodes in the network and allows for us to use machine learning algorithms for various prediction tasks on network data that have an inherently complex and disordered structure. Network node embedding should preserve as much information as possible about important network properties where information is stored, such as network structure and node properties, while representing nodes as numerical vectors in a lower-dimensional space than the original higher dimensional space. Superior node embedding algorithms are a powerful tool for machine learning with effective and efficient node representation. Recent research in representation learning has led to significant advances in automating features through unsupervised learning, inspired by advances in natural language processing. Here, we seek to improve the representation quality of node embeddings with a new node vectorization technique that uses network analysis to overcome network-based information loss. In this study, we introduce the NodeVector algorithm, which combines network analysis and neural networks to transfer information from the target network to node embedding. As a proof of concept, our experiments performed on different categories of network datasets showed that our method achieves better results than its competitors for target networks. This is the first study to produce node representation by unsupervised learning using the combination of network analysis and neural networks to consider network data structure. Based on experimental results, the use of network analysis, complex initial node representation, balanced negative sampling, and neural networks has a positive effect on the representation quality of network node embedding. |
| first_indexed | 2024-03-08T09:58:52Z |
| format | Article |
| id | doaj.art-82da80fa19874b67a709663fbba7b072 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T09:58:52Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-82da80fa19874b67a709663fbba7b0722024-01-29T13:44:23ZengMDPI AGApplied Sciences2076-34172024-01-0114277510.3390/app14020775NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep LearningVolkan Altuntas0Computer Engineering Department, Bursa Technical University, 16310 Yildirim, TurkeyNetwork node embedding captures structural and relational information of nodes in the network and allows for us to use machine learning algorithms for various prediction tasks on network data that have an inherently complex and disordered structure. Network node embedding should preserve as much information as possible about important network properties where information is stored, such as network structure and node properties, while representing nodes as numerical vectors in a lower-dimensional space than the original higher dimensional space. Superior node embedding algorithms are a powerful tool for machine learning with effective and efficient node representation. Recent research in representation learning has led to significant advances in automating features through unsupervised learning, inspired by advances in natural language processing. Here, we seek to improve the representation quality of node embeddings with a new node vectorization technique that uses network analysis to overcome network-based information loss. In this study, we introduce the NodeVector algorithm, which combines network analysis and neural networks to transfer information from the target network to node embedding. As a proof of concept, our experiments performed on different categories of network datasets showed that our method achieves better results than its competitors for target networks. This is the first study to produce node representation by unsupervised learning using the combination of network analysis and neural networks to consider network data structure. Based on experimental results, the use of network analysis, complex initial node representation, balanced negative sampling, and neural networks has a positive effect on the representation quality of network node embedding.https://www.mdpi.com/2076-3417/14/2/775node embeddingsnetwork analysisunsupervised learningnode classificationgraph representationspattern recognition |
| spellingShingle | Volkan Altuntas NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning Applied Sciences node embeddings network analysis unsupervised learning node classification graph representations pattern recognition |
| title | NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning |
| title_full | NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning |
| title_fullStr | NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning |
| title_full_unstemmed | NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning |
| title_short | NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning |
| title_sort | nodevector a novel network node vectorization with graph analysis and deep learning |
| topic | node embeddings network analysis unsupervised learning node classification graph representations pattern recognition |
| url | https://www.mdpi.com/2076-3417/14/2/775 |
| work_keys_str_mv | AT volkanaltuntas nodevectoranovelnetworknodevectorizationwithgraphanalysisanddeeplearning |