计算机科学
分类器(UML)
人工智能
杠杆(统计)
机器学习
嵌入
卷积神经网络
对抗制
理论计算机科学
作者
Huiting Hong,Xin Li,Yuangang Pan,Ivor W. Tsang
出处
期刊:IEEE Transactions on Knowledge and Data Engineering
[Institute of Electrical and Electronics Engineers]
日期:2020-01-01
卷期号:: 1-1
被引量:10
标识
DOI:10.1109/tkde.2020.3023589
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI