.png){kind=icon}
Return
Geometry interaction network alignment
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.06.077.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Network alignment plays an important role in many fields. The main task of network alignment is to find the node correspondence between different networks, i.e. whether they represent the same natural entity. Most existing alignment methods obtain the relevant information of nodes in the network through network representation learning technology, and then calculate the relationship between different nodes based on the node representations. These methods mostly focus on Euclidean geometry to learn node representations, does Euclidean space fit well with the network alignment? Considering that realworld networks often exhibit hierarchical structure and hyperbolic geometry shows the advantage of expressing network hierarchical structure, some researchers use hyperbolic geometry to learn node representations. But the network is not all hierarchical structure, so we exploit Euclidean and hyperbolic geometries jointly for node representation learning through an interactive learning mechanism to exploit the reliable spatial features in networks. The proposed method can well adapt to the complex structure in the network, providing efficient node representations for network alignment. Extensive experiments on synthetic and real-world datasets show the superiority of our method for network alignment. (c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Network alignment
Geometry interaction
Node representations
Hyperbolic embedding
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
View more organizations
Cited Papers
Structural Changes in South Korea's Rental Housing Market: The Rise and Fall of the Jeonse System
PREAI
ShareSaveMobile behavior trusted certification based on multivariate behavior sequences.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSaveShareSaveShareSave View more