.png){kind=icon}
.png){kind=icon}
Return
Domain-Adversarial Network Alignment
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2020.3023589.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Network alignment is a critical task in a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architecture (DANA) to obtain a domain-invariant representation for network alignment via an adversarial domain classifier. Specifically, we employ the graph convolutional networks to perform network embedding under the domain adversarial principle, given a small set of observed anchors. Then, the semi-supervised learning framework is optimized by maximizing a posterior probability distribution of observed anchors and the loss of a domain classifier simultaneously. We also develop a few variants of our model, such as, direction-aware network alignment, weight-sharing for directed networks and simplification of parameter space. Experiments on three real-world social network datasets demonstrate that our proposed approaches achieve state-of-the-art alignment results.
Keywords:
Task analysis
Social network services
Feature extraction
Support vector machines
Probability distribution
Proteins
Two dimensional displays
Network alignment
representation learning
adversarial learning
graph convolutional networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.4
Papers:
6.7K
Citations:
3.2W