Attributed Graph Embedding Based on Attention with Cluster
Graph embedding is of great significance for the research and analysis of graphs. Graph embedding aims to map nodes in the network to low-dimensional vectors while preserving information in the original graph of nodes. In recent years, the appearance of graph neural networks has significantly improv...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/23/4563 |
| _version_ | 1797462697101492224 |
|---|---|
| author | Bin Wang Yu Chen Jinfang Sheng Zhengkun He |
| author_facet | Bin Wang Yu Chen Jinfang Sheng Zhengkun He |
| author_sort | Bin Wang |
| collection | DOAJ |
| description | Graph embedding is of great significance for the research and analysis of graphs. Graph embedding aims to map nodes in the network to low-dimensional vectors while preserving information in the original graph of nodes. In recent years, the appearance of graph neural networks has significantly improved the accuracy of graph embedding. However, the influence of clusters was not considered in existing graph neural network (GNN)-based methods, so this paper proposes a new method to incorporate the influence of clusters into the generation of graph embedding. We use the attention mechanism to pass the message of the cluster pooled result and integrate the whole process into the graph autoencoder as the third layer of the encoder. The experimental results show that our model has made great improvement over the baseline methods in the node clustering and link prediction tasks, demonstrating that the embeddings generated by our model have excellent expressiveness. |
| first_indexed | 2024-03-09T17:40:19Z |
| format | Article |
| id | doaj.art-0c673022335c4c059c04985c458aec95 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T17:40:19Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-0c673022335c4c059c04985c458aec952023-11-24T11:35:39ZengMDPI AGMathematics2227-73902022-12-011023456310.3390/math10234563Attributed Graph Embedding Based on Attention with ClusterBin Wang0Yu Chen1Jinfang Sheng2Zhengkun He3School of Computer Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaGraph embedding is of great significance for the research and analysis of graphs. Graph embedding aims to map nodes in the network to low-dimensional vectors while preserving information in the original graph of nodes. In recent years, the appearance of graph neural networks has significantly improved the accuracy of graph embedding. However, the influence of clusters was not considered in existing graph neural network (GNN)-based methods, so this paper proposes a new method to incorporate the influence of clusters into the generation of graph embedding. We use the attention mechanism to pass the message of the cluster pooled result and integrate the whole process into the graph autoencoder as the third layer of the encoder. The experimental results show that our model has made great improvement over the baseline methods in the node clustering and link prediction tasks, demonstrating that the embeddings generated by our model have excellent expressiveness.https://www.mdpi.com/2227-7390/10/23/4563network representation learningattributed graph embeddinggraph autoencodergraph neural networks |
| spellingShingle | Bin Wang Yu Chen Jinfang Sheng Zhengkun He Attributed Graph Embedding Based on Attention with Cluster Mathematics network representation learning attributed graph embedding graph autoencoder graph neural networks |
| title | Attributed Graph Embedding Based on Attention with Cluster |
| title_full | Attributed Graph Embedding Based on Attention with Cluster |
| title_fullStr | Attributed Graph Embedding Based on Attention with Cluster |
| title_full_unstemmed | Attributed Graph Embedding Based on Attention with Cluster |
| title_short | Attributed Graph Embedding Based on Attention with Cluster |
| title_sort | attributed graph embedding based on attention with cluster |
| topic | network representation learning attributed graph embedding graph autoencoder graph neural networks |
| url | https://www.mdpi.com/2227-7390/10/23/4563 |
| work_keys_str_mv | AT binwang attributedgraphembeddingbasedonattentionwithcluster AT yuchen attributedgraphembeddingbasedonattentionwithcluster AT jinfangsheng attributedgraphembeddingbasedonattentionwithcluster AT zhengkunhe attributedgraphembeddingbasedonattentionwithcluster |