Multivariate time series (MTS) anomaly detection identifies abnormal patterns where each timestamp contains multiple variables. Existing MTS anomaly detection methods fall into three categories: reconstruction-based, prediction-based, and classifier-based methods. However, these methods face three key challenges: (1) Unsupervised learning methods, such as reconstruction-based and prediction-based methods, rely on error thresholds, which can lead to inaccuracies; (2) Semi-supervised methods mainly model normal dataand often underuse anomaly labels, limiting detection of subtle anomalies; (3) Supervised learning methods, such as classifier-based approaches, often fail to capture local relationships, incur high computational costs, and are constrained by the scarcity of labeled data. To address these limitations, we proposeMoon, a supervised modality conversion-based multivariate time series anomaly detection framework.Moonenhances the efficiency and accuracy of anomaly detection while providing detailed anomaly analysis reports. First,Moonintroduces a novel multivariate Markov Transition Field (MV-MTF) technique to convert numeric time series data into image representations, capturing relationships across variables and timestamps. Since numeric data retains unique patterns that cannot be fully captured by image conversion alone,Moonemploys a Multimodal-CNN to integrate numeric and image data through a feature fusion model with parameter sharing, enhancing training efficiency. Finally, a SHAP-based anomaly explainer identifies key variables contributing to anomalies, improving interpretability. Extensive experiments on six real-world MTS datasets demonstrate thatMoonoutperforms six state-of-the-art methods by up to 93% in efficiency, 4% in accuracy and, 10.8% in interpretation performance.

Blockchain technology has transformed financial services sectors by providing security, transparency, and immutability through decentralized ledger systems. However, while blockchain data can support a range of applications-such as user quality analysis, illegal activity detection, and transaction pattern identification-existing systems are restricted to basic queries on blocks and transactions due to their sequential data storage. To support queries more generally, we propose VGQ, the first verifiable graph query (VGQ) framework that enables efficient graph queries on blockchain systems without altering blockchain storage structures. VGQ integrates a query layer with an external graph database system and represents blockchain data as a directed transaction graph to improve the efficiency of graph query execution. To ensure reliable results, VGQ includes result verification with three key performance enhancing optimizations: (i) computing connected components to exclude irrelevant vertices and edges during verification; (ii) merging information from edges to accelerate completeness verification; and (iii) employing a dual pointer algorithm for efficient soundness verification. Experiments offer evidence that VGQ can improve on the state-of-the-art framework in terms of query efficiency by up to one order of magnitude and in terms of verification efficiency by up to two orders of magnitude.

Dynamic Graph Neural Networks (DGNNs) are effective at capturing multidimensional data and enable many important applications. As model training is computationally intensive, distributed DGNN training is employed to accommodate large data. Also, when training DGNNs, so-called sliding window training is used predominantly, as it enhances both accuracy and efficiency. However, current distributed frameworks-such as snapshot partitioning, chunk-based partitioning, and L -hop cache-based communication-free vertex partitioning-are inherently incompatible with sliding window training. While communication-based vertex partitioning supports sliding window training, its design for static graphs limits the effectiveness in distributed DGNN training. Specifically, existing partitioning strategies fail to optimize communication across snapshots, while existing cache reuse and communication scheduling strategies ignore opportunities for optimization between sliding windows. To support distributed sliding window training, we present SWASH, a scalable and flexible communication framework that utilizes a S liding W indow-based c A che SH aring technique. Specifically, we propose a flexible communication framework that supports ratio adjustment and timing selection, as well as hyperparameter settings and adaptive scheduling. We also propose a lightweight partitioning strategy tailored to sliding window-based DGNN training to reduce both partitioning and communication overheads. Finally, to alleviate decreases in accuracy due to reduced communication, we propose a cache-sharing technique based on sliding windows for sharing boundary vertex embeddings. Comprehensive experiments show that SWASH is capable of training speedups of an average of 9.44× over state-of-the-art frameworks while maintaining the accuracy of fully communicating, non-caching training frameworks.

Trajectory similarity computation in road networks is crucial for data analytics. However, both non-learning-based and learning-based methods face challenges. First, they suffer from low accuracy due to manual parameter selection for model training and the omission of key spatio-temporal features in road networks. Second, they have low efficiency, stemming from the high time complexity of similarity computation and the time-consuming training process. Third, learning-based methods struggle with poor model generality due to the small size of available training samples. To address these challenges, we propose an effective and efficient trajectory similarity learning framework for road networks, called SimRN. To our knowledge, SimRN is the first deep reinforcement learning (DRL) approach for trajectory similarity computation. Specifically, SimRN consists of three key modules: the spatio-temporal prompt information extraction (STP) module, the trajectory representation based on DRL (TrajRL) module, and the graph contrastive learning (GCL) module. The STP module captures spatio-temporal features from road networks to improve the training of the trajectory representation. The TrajRL module automatically selects optimal parameters and enables parallel training, improving both trajectory representation and the efficiency of similarity computations. The GCL module employs a self-supervised contrastive learning paradigm to generate sufficient samples while preserving spatial constraints and temporal dependencies of trajectories. Extensive experiments on two real-world datasets, compared with three state-of-the-art methods, show that SimRN: (i) improves accuracy by 20%–40%, (ii) achieves speedups of 2–4x, and (iii) demonstrates strong generality, enabling effective similarity learning with very small sample sizes.

Spatiotemporal trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent analyses. Thus, the qualities of embeddings are very important. Methods for pre-training embeddings, which leverage unlabeled trajectories for training universal embeddings, have shown promising applicability across different tasks, thus attracting considerable interest. However, research progress on this topic faces two key challenges: a lack of a comprehensive overview of existing methods, resulting in several related methods not being well-recognized, and the absence of a unified pipeline, complicating the development of new methods and the analysis of methods. We present UniTE, a survey and a unified pipeline for this domain. In doing so, we present a comprehensive list of existing methods for pre-training trajectory embeddings, which includes methods that either explicitly or implicitly employ pre-training techniques. Further, we present a unified and modular pipeline with publicly available underlying code, simplifying the process of constructing and evaluating methods for pre-training trajectory embeddings. Additionally, we contribute a selection of experimental results using the proposed pipeline on real-world datasets.

As large volumes of trajectory data accumulate, simplifying trajectories to reduce storage and querying costs is increasingly studied. Existing proposals face three main problems. First, they require numerous iterations to decide which GPS points to delete. Second, they focus only on the relationships between neighboring points (local information) while neglecting the overall structure (global information), reducing the global similarity between the simplified and original trajectories and making it difficult to maintain consistency in query results, especially for similarity-based queries. Finally, they fail to differentiate the importance of points with similar features, leading to suboptimal selection of points to retain the original trajectory information. We propose MLSimp, a novel Mutual Learning query-driven trajectory simplification framework that integrates two distinct models: GNN-TS, based on graph neural networks, and Diff-TS, based on diffusion models. GNN-TS evaluates the importance of a point according to its globality, capturing its correlation with the entire trajectory, and its uniqueness, capturing its differences from neighboring points. It also incorporates attention mechanisms in the GNN layers, enabling simultaneous data integration from all points within the same trajectory and refining representations, thus avoiding iterative processes. Diff-TS generates amplified signals to enable the retention of the most important points at low compression rates. Experiments involving eight baselines on three databases show that MLSimp reduces the simplification time by 42%--70% and improves query accuracy over simplified trajectories by up to 34.6%.

Dynamic Graph Neural Networks (DGNNs) have demonstrated exceptional performance at dynamic-graph analysis tasks. However, the costs exceed those incurred by other learning tasks, to the point where deployment on large-scale dynamic graphs is infeasible. Existing distributed frameworks that facilitate DGNN training are in their early stages and experience challenges such as communication bottlenecks, imbalanced workloads, and GPU memory overflow. We introduce DynaHB, a distributed framework for DGNN training using so-called Hybrid Batches. DynaHB reduces communication by means of vertex caching, and it ensures even data and workload distribution by means of load-aware vertex partitioning. DyanHB also features a novel hybrid-batch training mode that combines vertex-batch and snapshot-batch techniques, thereby reducing training time and GPU memory usage. Next, to further enhance the hybrid batch based approach, DynaHB integrates a reinforcement learning-based batch adjuster and a pipelined batch generator with a batch reservoir to reduce the cost of generating hybrid batches. Extensive experiments show that DynaHB is capable of up to a 93× and an average of 8.06× speedups over the state-of-the-art training framework.