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.

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.

Abstract With the development of location-based services, smart cities, and intelligent transportation, route planning has evolved beyond shortest path finding to satisfy user’s flexible travel purposes through the Optimal Routes with Collective Spatial Keywords (ORCSK) routing. Because different Points of Interest (POIs) contain different sets of keywords, the user usually needs to visit multiple POIs to fulfill all needs. Moreover, the POIs’ stop hardness (time and cost) also influences user experience, but it was ignored by the existing solutions. Therefore, this work proposes to extend the ORCSK problem into Skyline Optimal Routes with Collective Spatial Keyword (Sky-ORCSK) by considering both distance and stop hardness. Specifically, we first propose the IG-Sky algorithm from the spatial keyword search perspective by extending the IG-Tree. Then we propose the DA-Sky algorithm from the path enumeration perspective by extending our previous DA-CSK. Furthermore, five optimization strategies are proposed to improve efficiency by pruning the search space. Extensive experimental evaluations on real-world datasets demonstrate the algorithms’ efficacy and reliability, marking a significant step forward in refined route planning for modern urban environments.

The uniqueness of trajectory data for user re-identification has received unprecedented attention as the increasing popularity of location-based services boosts the excessive collection of daily trajectories with sufficient spatiotemporal coverage. Consequently, leveraging or releasing personally-sensitive trajectories without proper protection severely threatens individual privacy despite simply removing IDs. Trajectory privacy protection is never a trivial task due to the trade-off between privacy protection, utility preservation, and computational efficiency. Furthermore,recovery attack, one of the most threatening attacks specific to trajectory data, has not been well studied in the current literature. To tackle these challenges, we propose a frequency-based randomization model with a rigorous differential privacy guarantee for privacy-preserving trajectory data publishing. In particular, two randomized mechanisms are introduced for perturbing the local/global frequency distributions of a limited number of significantly essential locations in trajectories by injecting special Laplace noises. To reflect the perturbed distributions on the trajectory level without losing privacy guarantee or data utility, we formulate the trajectory modification tasks as kNN search problems and design two hierarchical indices with powerful pruning strategies and a novel search algorithm to support efficient modification. Extensive experiments on a real-world dataset verify the effectiveness of our approaches in resisting individual re-identification and recovery attacks simultaneously while still preserving desirable data utility. The efficient performance on large-scale data demonstrates the feasibility and scalability in practice.

Trajectory data has become ubiquitous nowadays, which can benefit various real-world applications such as traffic management and location-based services. However, trajectories may disclose highly sensitive information of an individual including mobility patterns, personal profiles and gazetteers, social relationships, etc, making it indispensable to consider privacy protection when releasing trajectory data. Ensuring privacy on trajectories demands more than hiding single locations, since trajectories are intrinsically sparse and high-dimensional, and require to protect multi-scale correlations. To this end, extensive research has been conducted to design effective techniques for privacy-preserving trajectory data publishing. Furthermore, protecting privacy requires carefully balance two metrics: privacy and utility. In other words, it needs to protect as much privacy as possible and meanwhile guarantee the usefulness of the released trajectories for data analysis. In this survey, we provide a comprehensive study and a systematic summarization of existing protection models, privacy and utility metrics for trajectories developed in the literature. We also conduct extensive experiments on two real-life public trajectory datasets to evaluate the performance of several representative privacy protection models, demonstrate the trade-off between privacy and utility, and guide the choice of the right privacy model for trajectory publishing given certain privacy and utility desiderata.

With the popularity of GPS-enabled devices, a huge amount of trajectory data has been continuously collected and a variety of location-based services have been developed that greatly benefit our daily life. However, the released trajectories also bring severe concern on personal privacy, and several recent studies have demonstrated the existence of personally-identifying information in spatial trajectories. Trajectory anonymization is nontrivial due to the trade-off between privacy protection and utility preservation. Furthermore, recovery attack has not been well studied in the current literature. To tackle these issues, we propose a frequency-based randomization model with a rigorous differential privacy guarantee for trajectory data publishing. In particular, we introduce two randomized mechanisms to perturb the local/global frequency distributions of significantly important locations in trajectories by injecting Laplace noise. We design a hierarchical indexing along with a novel search algorithm to support efficient trajectory modification, ensuring the modified trajectories satisfy the perturbed distributions without compromising privacy guarantee or data utility. Extensive experiments on a real-world trajectory dataset verify the effectiveness of our approaches in resisting individual re-identification and recovery attacks, and meanwhile preserving desirable data utility as well as the feasibility in practice.

Trajectory-based spatiotemporal entity linking is to match the same moving object in different datasets based on their movement traces. It is a fundamental step to support spatiotemporal data integration and analysis. In this paper, we study the problem of spatiotemporal entity linking using effective and concise signatures extracted from their trajectories. This linking problem is formalized as a$k$-nearest neighbor ($k$-NN) query on the signatures. Four representation strategies (sequential, temporal, spatial, and spatiotemporal) and two quantitative criteria (commonality and unicity) are investigated for signature construction. A simple yet effective dimension reduction strategy is developed together with a novel indexing structure called the WR-tree to speed up the search. A number of optimization methods are proposed to improve the accuracy and robustness of the linking. Our extensive experiments on real-world datasets verify the superiority of our approach over the state-of-the-art solutions in terms of both accuracy and efficiency.

The prevalent adoption of GPS-enabled devices has witnessed an explosion of various location-based services which produce a huge amount of trajectories monitoring an individual's movement. This triggers an interesting question: is movement history sufficiently representative and distinctive to identify an individual? In this work, we study the problem of moving object linking based on their historical traces. However, it is non-trivial to extract effective patterns from moving history and meanwhile conduct object linking efficiently. To this end, we propose four representation strategies (sequential, temporal, spatial, and spatiotemporal) and two quantitative criteria (commonality and unicity) to construct the personalised signature from the historical trace. Moreover, we formalise the problem of moving object linking as a k-nearest neighbour (k-NN) search on the collection of signatures, and aim to improve efficiency considering the high dimensionality of signatures and the large cardinality of the candidate object set. A simple but effective dimension reduction strategy is introduced in this work, which empirically outperforms existing algorithms including PCA and LSH. We propose a novel indexing structure, Weighted R-tree (WR-tree), and two pruning methods to further speed up k-NN search by combining weight and spatial information contained in the signature. Our extensive experimental results on a real world dataset verify the superiority of our proposals, in terms of both accuracy and efficiency, over state-of-the-art approaches.

Aligning users across multiple heterogeneous social networks is a fundamental issue in many data mining applications. Methods that incorporate user attributes and network structure have received much attention. However, most of them suffer from error propagation or the noise from diverse neighbors in the network. To effectively model the influence from neighbors, we propose a graph neural network to directly represent the ego networks of two users to be aligned into an embedding, based on which we predict the alignment label. Three major mechanisms in the model are designed to unitedly represent different attributes, distinguish different neighbors and capture the structure information of the ego networks respectively.