An Advanced Deep Generative Framework for Temporal Link Prediction in Dynamic Networks

Exploring Temporal Community Structure via Network Embedding

Temporal community detection is helpful to discover and analyze significant groups or clusters hidden in dynamic networks in the real world. A variety of methods, such as modularity optimization, spectral method, and statistical network model, has been developed from diversified perspectives. Recently, network embedding-based technologies have made significant progress, and one can exploit deep learning superiority to network tasks. Although some methods for static networks have shown promising results in boosting community detection by integrating community embedding, they are not suitable for temporal networks and unable to capture their dynamics. Furthermore, the dynamic embedding methods only model network varying without considering community structures. Hence, in this article, we propose a novel unsupervised dynamic community detection model, which is based on network embedding and can effectively discover temporal communities and model dynamic networks. More specifically, we propose the community prior by introducing the Gaussian mixture model (GMM) in the variational autoencoder, which can obtain community information and better model the evolutionary characteristics of community structure and node embedding by utilizing the variant of gated recurrent unit (GRU). Extensive experiments conducted in real-world and artificial networks demonstrate that our proposed model has a better effect on improving the accuracy of dynamic community detection.

Understanding Private Car Aggregation Effect via Spatio-Temporal Analysis of Trajectory Data

Understanding the private car aggregation effect is conducive to a broad range of applications, from intelligent transportation management to urban planning. However, this work is challenging, especially on weekends, due to the inefficient representations of spatiotemporal features for such aggregation effect and the considerable randomness of private car mobility on weekends. In this article, we propose a deep learning framework for a spatiotemporal attention network (STANet) with a neural algorithm logic unit (NALU), the so-called STANet-NALU, to understand the dynamic aggregation effect of private cars on weekends. Specifically: 1) we design an improved kernel density estimator (KDE) by defining a log-cosh loss function to calculate the spatial distribution of the aggregation effect with guaranteed robustness and 2) we utilize the stay time of private cars as a temporal feature to represent the nonlinear temporal correlation of the aggregation effect. Next, we propose a spatiotemporal attention module that separately captures the dynamic spatial correlation and nonlinear temporal correlation of the private car aggregation effect, and then we design a gate control unit to fuse spatiotemporal features adaptively. Further, we establish the STANet-NALU structure, which provides the model with numerical extrapolation ability to generate promising prediction results of the private car aggregation effect on weekends. We conduct extensive experiments based on real-world private car trajectories data. The results reveal that the proposed STANet-NALU outperforms the well-known existing methods in terms of various metrics, including the mean absolute error (MAE), root mean square error (RMSE), Kullback-Leibler divergence (KL), and R2.

A link prediction method for MANETs based on fast spatio-temporal feature extraction and LSGANs

Link prediction aims to learn meaningful features from networks to predict the possibility of topology. Most of the existing research on temporal link prediction is mainly aimed at networks with slow topology changes. They ignore the information of topology interval and link duration. This paper proposes a link prediction model named FastSTLSG. It can automatically analyze the features of the topology in a unified framework to effectively capture the spatio-temporal correlation of Mobile Ad Hoc Networks. First, we regard the changing topology as a chaotic system, transform it into a series of static snapshots based on the autocorrelation function; Next, the fast graph convolutional network efficiently analyses the topological relationships between nodes and reduces the computational complexity by importance sampling. Then, the gate recurrent unit captures the temporal correlation between snapshots. Finally, the fully connected layer reconstructs the topological structure. In addition, we take full advantage of least squares generative adversarial networks to further improve the performance of generator to obtain high-quality link prediction results. Extensive experiments on different datasets show that our FastSTLSG model obtains higher prediction accuracy compared with existing baseline models.