PRUNE: Preserving proximity and global ranking for network embedding
Journal
Advances in Neural Information Processing Systems
Journal Volume
2017-December
Pages
5258-5267
Date Issued
2017
Author(s)
Abstract
We investigate an unsupervised generative approach for network embedding. A multi-task Siamese neural network structure is formulated to connect embedding vectors and our objective to preserve the global node ranking and local proximity of nodes. We provide deeper analysis to connect the proposed proximity objective to link prediction and community detection in the network. We show our model can satisfy the following design properties: scalability, asymmetry, unity and simplicity. Experiment results not only verify the above design properties but also demonstrate the superior performance in learning-to-rank, classification, regression, and link prediction tasks. ? 2017 Neural information processing systems foundation. All rights reserved.
Subjects
Community detection; Design properties; Learning to rank; Link prediction; Network embedding; Neural network structures
Type
conference paper