Xiaoxian Yang

TL;DR: Experimental results on two large-scale LBSNs datasets show that the proposed model without noise injection can achieve better recommendation accuracy than several state-of-the-art techniques, and the proposed weighted noise injection approach can achieved better performance on privacy preserving than traditional one with a little cost on accuracy.

TL;DR: A local community detection algorithm for multi-layer complicated network based on the trust relation (MTLCD) to constrain the node tensor and it is found that this algorithm had higher accuracy and stability, and it can accurately reflect the local community structure which the core node belongs to.

TL;DR: A multi-task learning component is constructed and feature embedding by attention-based long short-term memory (LSTM) is conducted and the correlation between taxi pick-up and drop-off with 3D ResNet is captured and combined to simultaneously predict the taxi demand for pick- up and dropped-off in the next time interval.

TL;DR: This work transforms the problem of spam worker detection into a node classification problem in a crowdsourcing heterogeneous network in which the vectors of worker nodes are learned using network embedding and proposes an improved variable-length random walk algorithm based on node centrality.