To effectively explore the supply chain relationships among Small and Medium-sized Enterprises (SMEs), some remarkable progress in such a relation modeling problem, especially knowledge graph-based methods have been witnessed during these years. As a typical link prediction task, supply chain prediction can usually predict the unknown future relationship facts between SMEs by utilizing the historical semantic connections between entities in knowledge graphs (KGs). However, it is still a great challenge for existing models as seldom of them can consider both temporal dependency and cooperative correlation of the connectivity pattern along the timeline synergistically. Accordingly, we propose a novel framework to learn joint relational co-evolution in Spatial-Temporal Knowledge Graphs (STKG). Specifically, on the base of the constructed large-scale financial STKG, a multi-view relational sequences mining method is proposed to reveal the semantic information from ontological concepts. Furthermore, a relational co-evolution learning module is also developed to capture the regularity of evolving connectivity patterns from the spatial-temporal view. Meanwhile, a multiple random subspace representation learning layer is also designed to improve both compatibility and complementarity during knowledge aggregation. Experimental results on large-scale SMEs supply chain prediction tasks from four real-world industries in China have illustrated the effectiveness of the proposed model.

Autonomous vehicles have attracted increasing interest in recent years and decision making is a critical task for autonomous driving. To improve both the efficiency and safety of autonomous driving in various traffic scenarios, the target vehicle needs to timely make rational driving decisions according to its historical driving state and environment state. Therefore, a driving model based on Conditional Generative Adversarial Networks (CGAN) is proposed to imitate human driving behavior, which can generate the mapping from the current state to the driving decision. The proposed model not only exploits the spatiotemporal relationship of the observable driving states by leveraging the Convolutional LSTM (ConvLSTM) network, but also learns the different weight values of hidden features by utilizing the self-attention mechanism. Simulation results indicate that the proposed model is capable of generating human-like driving decisions and outperforms other reference models based on real traffic data.