Graph neural network (GNN)-based approaches have achieved remarkable success in temporal knowledge graph (TKG) reasoning. Despite these advances, two critical challenges remain: 1) inadequate modeling of local contextual dynamics, which limits the adaptability of entity and relation representations to specific queries and 2) inadequate mechanisms for handling emerging patterns, that is, novel interactions absent from historical data, which reduces predictive performance in dynamic environments. To address these limitations, we propose TCDR-PD, a temporal and contextual dynamic representation network with pattern decomposition. TCDR-PD introduces a temporal and contextual dynamic representation learning (TCDR) module to capture both global temporal trends and query-specific contextual dynamics, enabling more precise embeddings. Additionally, the pattern decomposition (PD) prediction module explicitly disentangles the prediction of recurring and emerging patterns, enabling tailored strategies to improve reasoning performance. Experiments on four benchmark datasets demonstrate that TCDR-PD outperforms state-of-the-art methods, effectively supporting stable reasoning over evolving TKGs.

Robustness is paramount for ensuring the reliability of knowledge graph models in safety-sensitive applications. While recent research has delved into adversarial attacks on static knowledge graph models, the exploration of more practical temporal knowledge graphs has been largely overlooked. To fill this gap, we present the Adaptive Temporal Perturbation Framework (ATPF), a novel adversarial attack framework aimed at probing the robustness of temporal knowledge graph (TKG) models. The general idea of ATPF is to inject perturbations into the victim model input to undermine the prediction. First, we propose the Temporal Perturbation Prioritization (TPP) algorithm, which identifies the optimal time sequence for perturbation injection before initiating attacks. Subsequently, we design the Rank-Based Edge Manipulation (RBEM) algorithm, enabling the generation of both edge addition and removal perturbations under black-box setting. With ATPF, we present two adversarial attack methods: the stringent ATPF-hard and the more lenient ATPF-soft, each imposing different perturbation constraints. Our experimental evaluations on the link prediction task for TKGs demonstrate the superior attack performance of our methods compared to baseline methods. Furthermore, we find that strategically placing a single perturbation often suffices to successfully compromise a target link.

The demand-responsive customized bus has been operated in real life, which is a crucial way to improve the service quality and efficiency of the urban public transportation system. Reasonable station and line planning can enhance customized bus competitiveness in residents’ travel mode. Most previous studies on optimizing customized bus lines rely on historical passenger volume and travel time to generate static schemes, but the actual operation process of customized bus is often in uncertain circumstances, such as road congestion. The static strategy will occur deviations in this situation. This study proposes a novel planning method to address the above issue. First, a spatiotemporal clustering algorithm is proposed to generate joint stations based on the passenger travel demand. Second, the method models the multiline customized bus optimization problem as a Markov decision process and uses a multiagent deep reinforcement learning algorithm to ensure effective training and response to incomplete information scenarios. Finally, the rationality of the proposed planning method is verified in a case study of customized bus area in Chongqing, China. Compared with the latest heuristic optimization algorithm, our method can effectively reduce the operating and passenger costs in complex environments.