Lai Y.-AHsu C.-CChen W.-HYeh M.-YSHOU-DE LIN2021-09-022021-09-02201710495258https://www.scopus.com/inward/record.uri?eid=2-s2.0-85046993501&partnerID=40&md5=41e181538c603c04e1ab9c399b4675a2https://scholars.lib.ntu.edu.tw/handle/123456789/581449We 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.Community detection; Design properties; Learning to rank; Link prediction; Network embedding; Neural network structuresconference paper2-s2.0-85046993501