Abstract | ||
---|---|---|
•Our model can embed new nodes without additional training.•Embedding nodes with Gaussian distributions captures the uncertainty of nodes.•Incorporating node attributes makes representations of nodes efficient and accurate. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.inffus.2019.01.005 | Information Fusion |
Keywords | Field | DocType |
Attributed heterogeneous network,Network embedding,Gaussian distribution | ENCODE,Embedding,Homogeneous,Theoretical computer science,Gaussian,Artificial intelligence,Heterogeneous network,Fuse (electrical),Artificial neural network,Mathematics,Machine learning,Feature learning | Journal |
Volume | ISSN | Citations |
50 | 1566-2535 | 1 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mengyue Liu | 1 | 1 | 0.34 |
Jun Liu | 2 | 178 | 25.96 |
Yihe Chen | 3 | 3 | 2.06 |
Meng Wang | 4 | 24 | 11.05 |
Hao Chen | 5 | 156 | 61.18 |
Qinghua Zheng | 6 | 1261 | 160.88 |