Abstract

Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.

Keywords

EmbeddingComputer scienceNode (physics)Theoretical computer scienceRepresentation (politics)Binary numberArtificial intelligenceMathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Pages
1476-1481
Citations
99
Access
Closed

External Links

Social Impact

Altmetric

Social media, news, blog, policy document mentions

Citation Metrics

99
OpenAlex

Cite This

Hong Yang, Shirui Pan, Peng Zhang et al. (2018). Binarized attributed network embedding. , 1476-1481. https://doi.org/10.1109/icdm.2018.8626170

Identifiers

DOI
10.1109/icdm.2018.8626170