Wen Hua

Temporal knowledge graph reasoning (TKGR) aims to predict future events by inferring missing entities with dynamic knowledge structures. Existing LLM-based reasoning methods prioritize contextual over structural relations, struggling to extract relevant subgraphs from dynamic graphs. This limits structural information understanding, leading to unstructured, hallucination-prone inferences especially with temporal inconsistencies. To address this problem, we propose IGETR (Integration of Graph and Editing-enhanced Temporal Reasoning), a hybrid reasoning framework that combines the structured temporal modeling capabilities of Graph Neural Networks (GNNs) with the contextual understanding of LLMs. IGETR operates through a three-stage pipeline. The first stage aims to ground the reasoning process in the actual data by identifying structurally and temporally coherent candidate paths through a temporal GNN, ensuring that inference starts from reliable graph-based evidence. The second stage introduces LLM-guided path editing to address logical and semantic inconsistencies, leveraging external knowledge to refine and enhance the initial paths. The final stage focuses on integrating the refined reasoning paths to produce predictions that are both accurate and interpretable. Experiments on standard TKG benchmarks show that IGETR achieves state-of-the-art performance, outperforming strong baselines with relative improvements of up to 5.6% on Hits@1 and 8.1% on Hits@3 on the challenging ICEWS datasets. Additionally, we execute ablation studies and additional analyses confirm the effectiveness of each component.

The popularity of location-aware devices has boosted urban systems with massive volumes of anonymous trajectory data, presenting both challenges and opportunities for enhancing smart city initiatives through Trajectory-User Linking (TUL). Typically, TUL aims to match anonymous trajectories with specific users by exploring spatiotemporal patterns and insightful mobility behaviors. However, current TUL models face significant limitations due to their reliance on singular data sources and insufficient consideration of real-world scenarios. Furthermore, these models often lack evaluation in fair and comprehensive environments, hindering accurate assessment of their performance and applicability. This paper systematically investigates prevalent challenges encountered by existing TUL models, conducts a comprehensive review of state-of-the-art models, and proposes a structured framework that encompasses three core components: point-level representation learning, trajectory-level representation learning, and user linking. Through meticulously designed experiments, we examine the effectiveness and efficiency of leading TUL models in handling the complexities of real-world data, such as data imbalance, sparsity, new users, and scalability. This in-depth analysis uncovers limitations in existing methodologies and offers guidance for future advancements, contributing to the development of robust TUL solutions for urban mobility analysis and smart city technologies.

Complex Query Answering (CQA) on knowledge graphs is a fundamental yet challenging task, which can be formalized as answering a subset of first-order logic queries containing logical conjunction, disjunction, negation, and existential quantifiers. Recent research reveals that Link Predictors (LPs) trained on 1-hop queries can generalize to various types of complex queries. However, existing methods neglect crucial characteristics of LPs’ outputs, including the effects of highly relevant entities and uncertainty. What’s worse, as they model logical operations by fuzzy set operations, these methods suffer from problems like inflexibility, sensitivity to noise, and inconsistency with priority in human cognition, which limits their performance, especially on queries with negation. To address these challenges, we propose an efficient fuzzy system for CQA that requires no extra training overhead and is plug-and-play with existing LP-based methods. First, we expand the output of LPs by two complementary membership functions of weak and strong relevance, which help to distinguish the target entities from highly relevant and irrelevant entities. Subsequently, we model logical operations through fuzzy rule bases and infer the final predictions via defuzzification, providing a flexible and tractable scheme for modeling logical operations. Finally, the effectiveness of the proposed fuzzy system is validated by its outstanding performance on benchmark datasets when compared to state-of-the-art methods. The source code of our proposed method is available at https://github.com/luyy9apples/FuzzSys-CQA.

Temporal entity alignment (TEA), which identifies equivalent entities across temporal knowledge graphs (TKGs), plays a vital role in integrating multiple TKGs.Simply adapting traditional EA models to TKGs cannot achieve satisfactory results, driving the need for dedicated studies in TEA. However, existing TEA models often fail to effectively capture the importance of temporal features and the richness of temporal context during embedding learning. Moreover, the challenge of temporal heterogeneity, which is prevalent in real-world TKGs, has not been adequately studied. In this work, we propose a HTEA framework to address these limitations. Specifically, we introduce a frequency-based temporal embedding module that incorporates the importance of temporal features for each entity, along with a temporal attention mechanism that prioritizes more informative context based on temporal richness. We further design an iterative module to detect temporal heterogeneity and refine the related facts accordingly. In this way, entity embeddings can be improved progressively, yielding more accurate and consistent alignment outcomes.Extensive experiments showcase the efficacy of our HTEA model, especially under the existence of temporal heterogeneity in real-world TKGs.