Please use this identifier to cite or link to this item:
Title: Predictive network representation learning for link prediction
Authors: Wang, Z 
Chen, C 
Li, W 
Keywords: Network Representation Learning
Link Prediction
Issue Date: 2017
Publisher: Association for Computing Machinary
Source: SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017, p. 969-972 How to cite?
Abstract: In this paper, we propose a predictive network representation learning (PNRL) model to solve the structural link prediction problem. The proposed model de-nes two learning objectives, i.e., observed structure preservation and hidden link prediction. To integrate the two objectives in a unified model, we develop an e-ective sampling strategy to select certain edges in a given network as assumed hidden links and regard the rest network structure as observed when training the model. By jointly optimizing the two objectives, the model can not only enhance the predictive ability of node representations but also learn additional link prediction knowledge in the representation space. Experiments on four real-world datasets demonstrate the superiority of the proposed model over the other popular and state-of-The-Art approaches.
ISBN: 9781450350228
DOI: 10.1145/3077136.3080692
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Nov 27, 2018

Page view(s)

Last Week
Last month
Citations as of Dec 3, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.