PRUNE: Preserving Proximity and Global Ranking for Network Embedding
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.
Cite
Text
Lai et al. "PRUNE: Preserving Proximity and Global Ranking for Network Embedding." Neural Information Processing Systems, 2017.Markdown
[Lai et al. "PRUNE: Preserving Proximity and Global Ranking for Network Embedding." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/lai2017neurips-prune/)BibTeX
@inproceedings{lai2017neurips-prune,
title = {{PRUNE: Preserving Proximity and Global Ranking for Network Embedding}},
author = {Lai, Yi-An and Hsu, Chin-Chi and Chen, Wen Hao and Yeh, Mi-Yen and Lin, Shou-De},
booktitle = {Neural Information Processing Systems},
year = {2017},
pages = {5257-5266},
url = {https://mlanthology.org/neurips/2017/lai2017neurips-prune/}
}