Attention‐based network embedding with higher‐order weights and node attributes
Abstract Network embedding aspires to learn a low‐dimensional vector of each node in networks, which can apply to diverse data mining tasks. In real‐life, many networks include rich attributes and temporal information. However, most existing embedding approaches ignore either temporal information or...
Main Authors: | Xian Mo, Binyuan Wan, Rui Tang, Junkai Ding, Guangdi Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-04-01
|
Series: | CAAI Transactions on Intelligence Technology |
Subjects: | |
Online Access: | https://doi.org/10.1049/cit2.12215 |
Similar Items
-
NAGNE: Node-to-Attribute Generation Network Embedding for Heterogeneous Network
by: Zheding Zhang, et al.
Published: (2024-01-01) -
Attributed Graph Embedding Based on Attention with Cluster
by: Bin Wang, et al.
Published: (2022-12-01) -
Attributed Stream Hypergraphs: temporal modeling of node-attributed high-order interactions
by: Andrea Failla, et al.
Published: (2023-06-01) -
Signed Network Node Embedding via Dual Attention Mechanism
by: Zekun Lu, et al.
Published: (2022-01-01) -
Effective attributed network embedding with information behavior extraction
by: Ganglin Hu, et al.
Published: (2022-07-01)