Back to Search
Start Over
Domain-Adversarial Network Alignment.
- Source :
- IEEE Transactions on Knowledge & Data Engineering; Jul2022, Vol. 34 Issue 7, p3211-3224, 14p
- Publication Year :
- 2022
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- DISTRIBUTION (Probability theory)
SOCIAL networks
Subjects
Details
- Language :
- English
- ISSN :
- 10414347
- Volume :
- 34
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Knowledge & Data Engineering
- Publication Type :
- Academic Journal
- Accession number :
- 157258592
- Full Text :
- https://doi.org/10.1109/TKDE.2020.3023589