Показать сокращенную информацию
An Algorithm of Dynamic Heterogeneous Networks Link Prediction
dc.contributor.advisor | Yu-hong, Zh. | |
dc.contributor.author | Hao, W. | |
dc.contributor.author | Xiang-ming, N. | |
dc.coverage.spatial | Гомель | ru_RU |
dc.date.accessioned | 2023-11-15T11:26:17Z | |
dc.date.available | 2023-11-15T11:26:17Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | Hao, W. An Algorithm of Dynamic Heterogeneous Networks Link Prediction / W. Hao, N. Xiang-ming ; науч. рук. Zh. Yu-hong // Исследования и разработки в области машиностроения, энергетики и управления : материалы XXIII Междунар. науч.-техн. конф. студентов, аспирантов и молодых ученых, Гомель, 27–28 апр. 2023 г. : в 2 ч. Ч. 2 / М-во образования Респ. Беларусь, Гомел. гос. техн. ун-т им. П. О. Сухого ; под общ. ред. А. А. Бойко. – Гомель : ГГТУ им. П. О. Сухого, 2023. – C. 310-312. | ru_RU |
dc.identifier.uri | https://elib.gstu.by/handle/220612/29287 | |
dc.description.abstract | By considering the evolution of networks over time and the rich semantic and structural characteristics of heterogeneous networks, DyMDGCN model is proposed in this paper. The model uses multi-channel partition to deal with heterogeneous networks, and then combines RNN and time attention capture evolution mode to obtain the final node embedding vector from and apply it to link prediction. In order to verify the effectiveness of this method, this paper selects two real dynamic heterogeneous network data sets of Twitter and EComm for experiments, and compares the AUC index with the traditional algorithm. The results show that this method can deal with heterogeneous network information and capture the dynamic evolution information of the network, and has a certain improvement in accuracy compared with the traditional algorithm. | ru_RU |
dc.language.iso | en | ru_RU |
dc.publisher | ГГТУ им. П.О. Сухого | ru_RU |
dc.subject | Dynamic network | ru_RU |
dc.subject | Heterogeneous network | ru_RU |
dc.subject | Link prediction | ru_RU |
dc.subject | DyMDGCN | ru_RU |
dc.subject | Time attention | ru_RU |
dc.subject | AUC | ru_RU |
dc.title | An Algorithm of Dynamic Heterogeneous Networks Link Prediction | ru_RU |
dc.type | Article | ru_RU |