Accurate travel time estimation (TTE) plays a crucial role in intelligent transportation systems. However, it remains challenging due to heterogeneous data sources and complex traffic dynamics. Moreover, traditional approaches typically convert trajectory data into fixed-length representations. This overlooks the inherent variability of real-world motion patterns, often resulting in information loss and redundancy. To address these challenges, this paper introduces the Multimodal Dynamic Trajectory Integration (MDTI) framework--a novel multimodal trajectory representation learning approach that integrates GPS sequences, grid trajectories, and road network constraints to enhance the performance of TTE. MDTI employs modality-specific encoders and a multimodal fusion module to capture complementary spatial, temporal, and topological semantics, while a dynamic trajectory modeling mechanism adaptively regulates information density for trajectories of varying lengths. Two self-supervised pretraining objectives, named contrastive alignment and masked language modeling, further strengthen multimodal consistency and contextual understanding. Extensive experiments on three real-world datasets demonstrate that MDTI consistently outperforms state-of-the-art baselines, confirming its robustness and strong generalization abilities. The code is publicly available at: https://github.com/City-Computing/MDTI.

Temporal Knowledge Graph (TKG) reasoning seeks to predict future events by analyzing historical data, where the effective leverage of both local and global historical facts proves crucial. Existing approaches employ graph neural networks (GNNs) and recurrent neural networks (RNNs) for local evolution patterns, complemented by statistical methods to enhance attention to global facts, demonstrating efficient predictive capabilities. However, traditional GNNs, constrained by their low-order neighborhood aggregation design, inherently fail to model potential high-order dependencies among facts. Furthermore, existing global history modeling approaches may introduce irrelevant historical information that interferes with prediction tasks. To address these limitations, we propose a Dual History-aware HyperGraph Network for TKG reasoning, namely DHHGN. Specifically, for local history modeling, we design a hybrid hypergraph-graph joint recurrent convolution module that simultaneously captures low-order neighborhood information and high-order interaction patterns among entities, employing a gating mechanism to adaptively blend their contributions. For global history modeling, we propose a dual history enhancement module that amplifies attention on pivotal historical facts while ensuring holistic integration of all historical contexts. Extensive experiments on four public benchmarks validate that DualHist-HGN consistently outperforms existing state-of-the-art methods across TKG reasoning tasks.

Temporal Knowledge Graph Completion (TKGC) aims to predict missing entities or relations based on historical facts, thereby facilitating the understanding of dynamic system evolution and supporting downstream reasoning tasks. However, existing methods predominantly focus on modeling sequential and structural dependencies, often overlooking the rich semantic information embedded in entities and relations, as well as the higher-order interactions among them, which limits their ability to handle complex, evolving scenarios effectively. To address these limitations, we propose DSTAG, a novel TKGC approach based on a semantic tag-enhanced dual-graph convolutional network. Our method leverages large language models to generate contextualized semantic multi-tags for both entities and relations (e.g., ''political event,'' ''economic activity''), thereby enriching their semantic representations. Furthermore, we introduce a semantic tag representation mechanism that captures higher-order dependencies during the aggregation and propagation of semantic tag information across graphs. DSTAG adopts a dual-graph convolutional network architecture, where the relation graph convolution extracts semantic features between temporal relationships and injects this information into the entity graph convolution, enabling joint modeling of entities and relations. We evaluate DSTAG on three widely used TKG benchmarks: ICEWS14, ICEWS18, and ICEWS05-15. Experimental results show that DSTAG achieves substantial MRR improvements over state-of-the-art baselines by 8.64%, 9.81% and 4.56%, respectively.

The Transformer model, with its ability to capture long-term dependencies, has demonstrated significant potential in enhancing long-term traffic flow prediction for effective urban transportation management. However, most existing Transformer-based methods adhere to a centralized approach, failing to address privacy concerns and to optimize computational resource utilization. Although emerging federated learning paradigms offer privacy protection, the average aggregation still overlooks client heterogeneity and lacks the synchronous efficiency required for traffic flow prediction tasks. Consequently, we introduce FedTFormer, a hierarchical federated learning framework tailored to boost the performance of Transformer models in decentralized environments, involving clients, edge servers, and a central server. Initially, clients are organized into clusters through a sophisticated static clustering mechanism anchored in bipartite graph theory. FedTFormer enhances robustness of Transformer by facilitating synchronous average aggregation within clusters. Additionally, it performs asynchronous fine-tuning of cluster-specific parameters, leveraging hypernetwork constructed on the central server. Clients utilize an optimized Transformer model for localized training, harnessing its proficiency in capturing long-term spatio-temporal dependencies. Ultimately, we conduct extensive experiments across three datasets, comparing our method against ten sophisticated approaches and demonstrating the effectiveness and robustness of FedTFormer.

Federated Graph Learning (FGL) has emerged as a key paradigm for distributed graph machine learning, enabling cross-domain graph collaborative modeling while preserving data privacy. However, existing methods face two major bottlenecks: the structural heterogeneity discrepancy of graph data among clients weakens the generalization ability of the global model; and model heterogeneity leads to inefficient knowledge sharing and complex global aggregation. To address these issues, we propose FedGVD, an efficient framework that constructs a global perspective through data condensation and server-side virtual node generation, which not only preserves the semantic equivalence of the original data but also avoids privacy leakage. Subsequently, by distributing low-dimensional generalizable knowledge for unidirectional distillation, FedGVD enables local models to absorb global knowledge without transmitting local parameters, thus breaking through the challenges of data and structural heterogeneity as well as model heterogeneity. This innovative approach ensures privacy-preserving and efficient federated graph collaboration. Experiments show that FedGVD maintains excellent performance in heterogeneous model scenarios while significantly improving communication efficiency, offering a new approach for privacy-preserving collaborative modeling in FGL. The code is available at https://github.com/Jasonxx4/FedGVD.

Temporal knowledge graph completion (TKGC) seeks to develop more comprehensive knowledge representations by addressing missing relationships and entities within temporal knowledge graphs (TKGs), thereby enhancing reasoning and predictive capabilities in downstream tasks. Nonetheless, real-world knowledge-such as the progression of social network interactions and the unfolding of news events-is inherently dynamic, resulting in substantial sparsity issues in TKGs that profoundly impair the performance of TKGC models. To overcome this challenge, we introduce the Adaptive Neighborhood Enhancement Layer (ANEL), a novel module that can be effortlessly integrated into existing TKGC models to substantially elevate the representation quality of sparse entities. ANEL first derives initial entity embeddings through a base model and then uncovers concealed semantic relationships between entities via a latent relation module, enriching the explicit relationships within the knowledge graph. Furthermore, ANEL incorporates an adaptive latent information adjustment component, which dynamically calibrates the influence of latent information based on the entity's relational structure: entities with fewer connections derive greater benefit from latent information, while entities with denser connections become less dependent on latent augmentation, ensuring precise and resilient representations. We conducted comprehensive experiments on four prominent benchmark datasets, and the results underscore the effectiveness and superiority of ANEL in TKGC tasks.

The primary objective of graph node anomaly detection is to pinpoint rare patterns that display marked deviations from the typical one. Existing methods utilize Graph Convolutional Networks (GCNs) to model complex interactions in Heterogeneous Information Networks (HINs), typically homogenizing HINs using meta-paths to effectively focus on particular semantic scenarios. However, meta-paths excessively emphasize specific nodes and their connections on predefined paths, leading to the neglect of one-hop context-rich neighbors. Furthermore, the conversion from heterogeneous to homogeneous structures disrupts inherent relationships, resulting in an irreversible loss of direct links. Thus, we propose a dual-view-based H eterogeneous I nformation N etworks Node Ano maly Detection framework, HINAno, to mitigate structural loss. HINAno adopts a synergetic approach that balances local structural information with semantic richness, drawing from both the one-hop neighbor view and the meta-path view. Specifically, this dual-view utilizes hierarchical fusion mechanisms at node, type, and semantic levels to capture one-hop and multi-hop neighborhoods in a level-wise manner. In addition, HINAno adopts self-supervised contrastive learning and GCNs to amplify the gap between normal and abnormal nodes, thereby reducing the reliance on anomalous labels and enhancing the capability of anomaly detection. Finally, we successfully verify that the HINAno framework is effective and superior on four real-world datasets.

Predicting traffic accidents can help traffic management departments respond to sudden traffic situations promptly, improve drivers’ vigilance, and reduce losses caused by traffic accidents. However, the causality of traffic accidents is complex and difficult to analyze. Most existing traffic accident prediction methods do not consider the dynamic spatio-temporal correlation of traffic data, which leads to unsatisfactory prediction accuracy. To address this issue, we propose a multi-task learning framework (TAP) based on the Spatio-temporal Variational Graph Auto-Encoders (ST-VGAE) for traffic accident profiling. We firstly capture the dynamic spatio-temporal correlation of traffic conditions through a spatio-temporal graph convolutional encoder and embed it as a low-latitude vector. Then, we use a multi-task learning scheme to combine external factors to generate the traffic accident profiling. Furthermore, we propose a traffic accident profiling application framework based on edge computing. This method increases the speed of calculation by offloading the calculation of traffic accident profiling to edge nodes. Finally, the experimental results on real datasets demonstrate that TAP outperforms other state-of-the-art baselines.