Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionComputer Science Program
KAUST Grant Number
FCC/1/1976-19-01Date
2019-03-11Online Publication Date
2019-03-11Print Publication Date
2019Permanent link to this record
http://hdl.handle.net/10754/631764
Metadata
Show full item recordAbstract
Existing embedding methods for attributed networks aim at learning low-dimensional vector representations for nodes only but not for both nodes and attributes, resulting in the fact that they cannot capture the affinities between nodes and attributes. However, capturing such affinities is of great importance to the success of many real-world attributed network applications, such as attribute inference and user profiling. Accordingly, in this paper, we introduce a Co-embedding model for Attributed Networks (CAN), which learns low-dimensional representations of both attributes and nodes in the same semantic space such that the affinities between them can be effectively captured and measured. To obtain high-quality embeddings, we propose a variational auto-encoder that embeds each node and attribute with means and variances of Gaussian distributions. Experimental results on real-world networks demonstrate that our model yields excellent performance in a number of applications compared with state-of-the-art techniques.Citation
Meng Z, Liang S, Bao H, Zhang X (2019) Co-Embedding Attributed Networks. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining - WSDM ’19. Available: http://dx.doi.org/10.1145/3289600.3291015.Sponsors
The research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST), under award number FCC/1/1976-19-01.Journal
Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining - WSDM '19Conference/Event name
12th ACM International Conference on Web Search and Data Mining, WSDM 2019Additional Links
https://dl.acm.org/citation.cfm?doid=3289600.3291015ae974a485f413a2113503eed53cd6c53
10.1145/3289600.3291015