Search

Time series forecasting has important applications across diverse domains. EasyTime, the system we demonstrate, facilitates easy use of time-series forecasting methods by researchers and practitioners alike. First, EasyTime enables one-click evaluation, enabling researchers to evaluate new forecasting methods using the suite of diverse time series datasets collected in the preexisting time series forecasting benchmark (TFB). This is achieved by leveraging TFB's flexible and consistent evaluation pipeline. Second, when practitioners must perform forecasting on a new dataset, a nontrivial first step is often to find an appropriate forecasting method. EasyTime provides an Automated Ensemble module that combines the promising forecasting methods to yield superior forecasting accuracy compared to individual methods. Third, EasyTime offers a natural language Q&A module leveraging large language models. Given a question like "Which method is best for long term forecasting on time series with strong seasonality?", EasyTime converts the question into SQL queries on the database of results obtained by TFB and then returns an answer in natural language and charts. By demonstrating EasyTime, we intend to show how it is possible to simplify the use of time series forecasting and to offer better support for the development of new generations of time series forecasting methods., Comment: Accepted by ICDE2025

Graph stream summarization refers to the process of processing a continuous stream of edges that form a rapidly evolving graph. The primary challenges in handling graph streams include the impracticality of fully storing the ever-growing datasets and the complexity of supporting graph queries that involve both topological and temporal information. Recent advancements, such as PGSS and Horae, address these limitations by using domain-based, top-down multi-layer structures in the form of compressed matrices. However, they either suffer from poor query accuracy, incur substantial space overheads, or have low query efficiency. This study proposes a novel item-based, bottom-up hierarchical structure, called HIGGS. Unlike existing approaches, HIGGS leverages its hierarchical structure to localize storage and query processing, thereby confining changes and hash conflicts to small and manageable subtrees, yielding notable performance improvements. HIGGS offers tighter theoretical bounds on query accuracy and space cost. Extensive empirical studies on real graph streams demonstrate that, compared to state-of-the-art methods, HIGGS is capable of notable performance enhancements: it can improve accuracy by over 3 orders of magnitude, reduce space overhead by an average of 30%, increase throughput by more than 5 times, and decrease query latency by nearly 2 orders of magnitude.

Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing TRL methods often produce vectors that, when used in downstream tasks, yield insufficiently accurate results. A key reason is that they fail to utilize the comprehensive information encompassed by trajectories. We propose a self-supervised TRL framework, called RED, which effectively exploits multiple types of trajectory information. Overall, RED adopts the Transformer as the backbone model and masks the constituting paths in trajectories to train a masked autoencoder (MAE). In particular, RED considers the moving patterns of trajectories by employing a Road-aware masking strategy} that retains key paths of trajectories during masking, thereby preserving crucial information of the trajectories. RED also adopts a spatial-temporal-user joint Embedding scheme to encode comprehensive information when preparing the trajectories as model inputs. To conduct training, RED adopts Dual-objective task learning}: the Transformer encoder predicts the next segment in a trajectory, and the Transformer decoder reconstructs the entire trajectory. RED also considers the spatial-temporal correlations of trajectories by modifying the attention mechanism of the Transformer. We compare RED with 9 state-of-the-art TRL methods for 4 downstream tasks on 3 real-world datasets, finding that RED can usually improve the accuracy of the best-performing baseline by over 5%., Comment: This paper is accepted by VLDB2025

Trajectory representation learning (TRL) maps trajectories to vectors that can be used for many downstream tasks. Existing TRL methods use either grid trajectories, capturing movement in free space, or road trajectories, capturing movement in a road network, as input. We observe that the two types of trajectories are complementary, providing either region and location information or providing road structure and movement regularity. Therefore, we propose a novel multimodal TRL method, dubbed GREEN, to jointly utilize Grid and Road trajectory Expressions for Effective representatioN learning. In particular, we transform raw GPS trajectories into both grid and road trajectories and tailor two encoders to capture their respective information. To align the two encoders such that they complement each other, we adopt a contrastive loss to encourage them to produce similar embeddings for the same raw trajectory and design a mask language model (MLM) loss to use grid trajectories to help reconstruct masked road trajectories. To learn the final trajectory representation, a dual-modal interactor is used to fuse the outputs of the two encoders via cross-attention. We compare GREEN with 7 state-of-the-art TRL methods for 3 downstream tasks, finding that GREEN consistently outperforms all baselines and improves the accuracy of the best-performing baseline by an average of 15.99\%., Comment: This paper is accepted by KDD2025(August Cycle)

Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically designed models achieve higher accuracy than manually designed models. Given a forecasting task, which includes a dataset and a forecasting horizon, automated design methods automatically search for an optimal forecasting model for the task in a manually designed search space, and then train the identified model using the dataset to enable the forecasting. Existing automated methods face three challenges. First, the search space is constructed by human experts, rending the methods only semi-automated and yielding search spaces prone to subjective biases. Second, it is time consuming to search for an optimal model. Third, training the identified model for a new task is also costly. These challenges limit the practicability of automated methods in real-world settings. To contend with the challenges, we propose a fully automated and highly efficient correlated time series forecasting framework where the search and training can be done in minutes. The framework includes a data-driven, iterative strategy to automatically prune a large search space to obtain a high-quality search space for a new forecasting task. It includes a zero-shot search strategy to efficiently identify the optimal model in the customized search space. And it includes a fast parameter adaptation strategy to accelerate the training of the identified model. Experiments on seven benchmark datasets offer evidence that the framework is capable of state-of-the-art accuracy and is much more efficient than existing methods., Comment: accepted by PVLDB 2025

The expanding instrumentation of processes throughout society with sensors yields a proliferation of time series data that may in turn enable important applications, e.g., related to transportation infrastructures or power grids. Machine-learning based methods are increasingly being used to extract value from such data. We provide means of reducing the resulting considerable computational and data storage costs. We achieve this by providing means of condensing large time series datasets such that models trained on the condensed data achieve performance comparable to those trained on the original, large data. Specifically, we propose a time series dataset condensation framework, TimeDC, that employs two-fold modal matching, encompassing frequency matching and training trajectory matching. Thus, TimeDC performs time series feature extraction and decomposition-driven frequency matching to preserve complex temporal dependencies in the reduced time series. Further, TimeDC employs curriculum training trajectory matching to ensure effective and generalized time series dataset condensation. To avoid memory overflow and to reduce the cost of dataset condensation, the framework includes an expert buffer storing pre-computed expert trajectories. Extensive experiments on real data offer insight into the effectiveness and efficiency of the proposed solutions., Comment: Accepted by PVLDB 2025

In large venues like shopping malls and airports, knowledge on the indoor populations fuels applications such as business analytics, venue management, and safety control. In this work, we provide means of modeling populations in partitions of indoor space offline and of monitoring indoor populations continuously, by using indoor positioning data. However, the low-sampling rates of indoor positioning render the data temporally and spatially sparse, which in turn renders the offline capture of indoor populations challenging. It is even more challenging to continuously monitor indoor populations, as positioning data may be missing or not ready yet at the current moment. To address these challenges, we first enable probabilistic modeling of populations in indoor space partitions as Normal distributions. Based on that, we propose two learning-based estimators for on-the-fly prediction of population distributions. Leveraging the prediction-based schemes, we provide a unified continuous query processing framework for a type of query that enables continuous monitoring of populated partitions. The framework encompasses caching and result validity mechanisms to reduce cost and maintain monitoring effectiveness. Extensive experiments on two real data sets show that the proposed estimators are able to outperform the state-of-the-art alternatives and that the query processing framework is effective and efficient., Comment: Accepted at TKDE

Due to the global trend towards urbanization, people increasingly move to and live in cities that then continue to grow. Traffic forecasting plays an important role in the intelligent transportation systems of cities as well as in spatio-temporal data mining. State-of-the-art forecasting is achieved by deep-learning approaches due to their ability to contend with complex spatio-temporal dynamics. However, existing methods assume the input is fixed-topology road networks and static traffic time series. These assumptions fail to align with urbanization, where time series are collected continuously and road networks evolve over time. In such settings, deep-learning models require frequent re-initialization and re-training, imposing high computational costs. To enable much more efficient training without jeopardizing model accuracy, we propose the Topological Evolution-aware Framework (TEAM) for traffic forecasting that incorporates convolution and attention. This combination of mechanisms enables better adaptation to newly collected time series, while being able to maintain learned knowledge from old time series. TEAM features a continual learning module based on the Wasserstein metric that acts as a buffer that can identify the most stable and the most changing network nodes. Then, only data related to stable nodes is employed for re-training when consolidating a model. Further, only data of new nodes and their adjacent nodes as well as data pertaining to changing nodes are used to re-train the model. Empirical studies with two real-world traffic datasets offer evidence that TEAM is capable of much lower re-training costs than existing methods are, without jeopardizing forecasting accuracy., Comment: 16 pages. An extended version of "TEAM: Topological Evolution-aware Framework for Traffic Forecasting" accepted at PVLDB 2025

Time Series Forecasting (TSF) is key functionality in numerous fields, including in finance, weather services, and energy management. While TSF methods are emerging these days, many of them require domain-specific data collection and model training and struggle with poor generalization performance on new domains. Foundation models aim to overcome this limitation. Pre-trained on large-scale language or time series data, they exhibit promising inferencing capabilities in new or unseen data. This has spurred a surge in new TSF foundation models. We propose a new benchmark, FoundTS, to enable thorough and fair evaluation and comparison of such models. FoundTS covers a variety of TSF foundation models, including those based on large language models and those pretrained on time series. Next, FoundTS supports different forecasting strategies, including zero-shot, few-shot, and full-shot, thereby facilitating more thorough evaluations. Finally, FoundTS offers a pipeline that standardizes evaluation processes such as dataset splitting, loading, normalization, and few-shot sampling, thereby facilitating fair evaluations. Building on this, we report on an extensive evaluation of TSF foundation models on a broad range of datasets from diverse domains and with different statistical characteristics. Specifically, we identify pros and cons and inherent limitations of existing foundation models, and we identify directions for future model design. We make our code and datasets available at https://anonymous.4open.science/r/FoundTS-C2B0.

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achieving state-of-the-art results in keyword spotting tasks, their effectiveness for more complex tasks such as sentence-level ASR remains unexplored. Additionally, the impact of the number of forward diffusion steps on performance is not well understood. In this paper, we systematically investigate the use of DMs for defending against adversarial attacks on sentences and examine the effect of varying forward diffusion steps. Through comprehensive experiments on the Mozilla Common Voice dataset, we demonstrate that two forward diffusion steps can completely defend against adversarial attacks on sentences. Moreover, we introduce a novel, training-free approach for detecting adversarial attacks by leveraging a pre-trained DM. Our experimental results show that this method can detect adversarial attacks with high accuracy., Comment: Under review at ICASSP 2025

Range-filtering approximate nearest neighbor (RFANN) search is attracting increasing attention in academia and industry. Given a set of data objects, each being a pair of a high-dimensional vector and a numeric value, an RFANN query with a vector and a numeric range as parameters returns the data object whose numeric value is in the query range and whose vector is nearest to the query vector. To process this query, a recent study proposes to build $O(n^2)$ dedicated graph-based indexes for all possible query ranges to enable efficient processing on a database of $n$ objects. As storing all these indexes is prohibitively expensive, the study constructs compressed indexes instead, which reduces the memory consumption considerably. However, this incurs suboptimal performance because the compression is lossy. In this study, instead of materializing a compressed index for every possible query range in preparation for querying, we materialize graph-based indexes, called elemental graphs, for a moderate number of ranges. We then provide an effective and efficient algorithm that during querying can construct an index for any query range using the elemental graphs. We prove that the time needed to construct such an index is low. We also cover an experimental study on real-world datasets that provides evidence that the materialized elemental graphs only consume moderate space and that the proposed method is capable of superior and stable query performance across different query workloads., Comment: The paper has been accepted by SIGMOD 2025

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. Implementation of the pipeline is publicly available at https://github.com/Logan-Lin/UniTE.

The availability of massive vehicle trajectory data enables the modeling of road-network constrained movement as travel-cost distributions rather than just single-valued costs, thereby capturing the inherent uncertainty of movement and enabling improved routing quality. Thus, stochastic routing has been studied extensively in the edge-centric model, where such costs are assigned to the edges in a graph representation of a road network. However, as this model still disregards important information in trajectories and fails to capture dependencies among cost distributions, a path-centric model, where costs are assigned to paths, has been proposed that captures dependencies better and provides an improved foundation for routing. Unfortunately, when applied in this model, existing routing algorithms are inefficient due to two shortcomings that we eliminate. First, when exploring candidate paths, existing algorithms only consider the costs of candidate paths from the source to intermediate vertices, while disregarding the costs of travel from the intermediate vertices to the destination, causing many non-competitive paths to be explored. We propose two heuristics for estimating the cost from an intermediate vertex to the destination, thus improving routing efficiency. Second, the edge-centric model relies on stochastic dominance-based pruning to improve efficiency. This pruning assumes that costs are independent and is therefore inapplicable in the path-centric model that takes dependencies into account. We introduce a notion of virtual path that effectively enables stochastic dominance-based pruning in the path-based model, thus further improving efficiency. Empirical studies using two real-world trajectory sets offer insight into the properties of the proposed solution, indicating that it enables efficient stochastic routing in the path-centric model.

This paper focuses on the integration of generative techniques into spatial-temporal data mining, considering the significant growth and diverse nature of spatial-temporal data. With the advancements in RNNs, CNNs, and other non-generative techniques, researchers have explored their application in capturing temporal and spatial dependencies within spatial-temporal data. However, the emergence of generative techniques such as LLMs, SSL, Seq2Seq and diffusion models has opened up new possibilities for enhancing spatial-temporal data mining further. The paper provides a comprehensive analysis of generative technique-based spatial-temporal methods and introduces a standardized framework specifically designed for the spatial-temporal data mining pipeline. By offering a detailed review and a novel taxonomy of spatial-temporal methodology utilizing generative techniques, the paper enables a deeper understanding of the various techniques employed in this field. Furthermore, the paper highlights promising future research directions, urging researchers to delve deeper into spatial-temporal data mining. It emphasizes the need to explore untapped opportunities and push the boundaries of knowledge to unlock new insights and improve the effectiveness and efficiency of spatial-temporal data mining. By integrating generative techniques and providing a standardized framework, the paper contributes to advancing the field and encourages researchers to explore the vast potential of generative techniques in spatial-temporal data mining., Comment: 19 pages

The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e.g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal prediction is often essential to enable safety, predictability, or reliability. Many recent proposals that target deep learning for spatio-temporal prediction suffer from so-called catastrophic forgetting, where previously learned knowledge is entirely forgotten when new data arrives. Such proposals may experience deteriorating prediction performance when applied in settings where data streams into the system. To enable spatio-temporal prediction on streaming data, we propose a unified replay-based continuous learning framework. The framework includes a replay buffer of previously learned samples that are fused with training data using a spatio-temporal mixup mechanism in order to preserve historical knowledge effectively, thus avoiding catastrophic forgetting. To enable holistic representation preservation, the framework also integrates a general spatio-temporal autoencoder with a carefully designed spatio-temporal simple siamese (STSimSiam) network that aims to ensure prediction accuracy and avoid holistic feature loss by means of mutual information maximization. The framework further encompasses five spatio-temporal data augmentation methods to enhance the performance of STSimSiam. Extensive experiments on real data offer insight into the effectiveness of the proposed framework., Comment: Accepted by ICDE 2024

We are witnessing an increasing availability of streaming data that may contain valuable information on the underlying processes. It is thus attractive to be able to deploy machine learning models on edge devices near sensors such that decisions can be made instantaneously, rather than first having to transmit incoming data to servers. To enable deployment on edge devices with limited storage and computational capabilities, the full-precision parameters in standard models can be quantized to use fewer bits. The resulting quantized models are then calibrated using back-propagation and full training data to ensure accuracy. This one-time calibration works for deployments in static environments. However, model deployment in dynamic edge environments call for continual calibration to adaptively adjust quantized models to fit new incoming data, which may have different distributions. The first difficulty in enabling continual calibration on the edge is that the full training data may be too large and thus not always available on edge devices. The second difficulty is that the use of back-propagation on the edge for repeated calibration is too expensive. We propose QCore to enable continual calibration on the edge. First, it compresses the full training data into a small subset to enable effective calibration of quantized models with different bit-widths. We also propose means of updating the subset when new streaming data arrives to reflect changes in the environment, while not forgetting earlier training data. Second, we propose a small bit-flipping network that works with the subset to update quantized model parameters, thus enabling efficient continual calibration without back-propagation. An experimental study, conducted with real-world data in a continual learning setting, offers insight into the properties of QCore and shows that it is capable of outperforming strong baseline methods., Comment: 15 pages. An extended version of "QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models" accepted at PVLDB 2024

Time series are generated in diverse domains such as economic, traffic, health, and energy, where forecasting of future values has numerous important applications. Not surprisingly, many forecasting methods are being proposed. To ensure progress, it is essential to be able to study and compare such methods empirically in a comprehensive and reliable manner. To achieve this, we propose TFB, an automated benchmark for Time Series Forecasting (TSF) methods. TFB advances the state-of-the-art by addressing shortcomings related to datasets, comparison methods, and evaluation pipelines: 1) insufficient coverage of data domains, 2) stereotype bias against traditional methods, and 3) inconsistent and inflexible pipelines. To achieve better domain coverage, we include datasets from 10 different domains: traffic, electricity, energy, the environment, nature, economic, stock markets, banking, health, and the web. We also provide a time series characterization to ensure that the selected datasets are comprehensive. To remove biases against some methods, we include a diverse range of methods, including statistical learning, machine learning, and deep learning methods, and we also support a variety of evaluation strategies and metrics to ensure a more comprehensive evaluations of different methods. To support the integration of different methods into the benchmark and enable fair comparisons, TFB features a flexible and scalable pipeline that eliminates biases. Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8,068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets. The benchmark code and data are available at https://github.com/decisionintelligence/TFB., Comment: Directly accepted by PVLDB 2024

Graph augmentation with contrastive learning has gained significant attention in the field of recommendation systems due to its ability to learn expressive user representations, even when labeled data is limited. However, directly applying existing GCL models to real-world recommendation environments poses challenges. There are two primary issues to address. Firstly, the lack of consideration for data noise in contrastive learning can result in noisy self-supervised signals, leading to degraded performance. Secondly, many existing GCL approaches rely on graph neural network (GNN) architectures, which can suffer from over-smoothing problems due to non-adaptive message passing. To address these challenges, we propose a principled framework called GraphAug. This framework introduces a robust data augmentor that generates denoised self-supervised signals, enhancing recommender systems. The GraphAug framework incorporates a graph information bottleneck (GIB)-regularized augmentation paradigm, which automatically distills informative self-supervision information and adaptively adjusts contrastive view generation. Through rigorous experimentation on real-world datasets, we thoroughly assessed the performance of our novel GraphAug model. The outcomes consistently unveil its superiority over existing baseline methods. The source code for our model is publicly available at: https://github.com/HKUDS/GraphAug., Comment: 13 pages and accepted by ICDE 2024

The squeezing process of a three-dimensional quantum system by use of an external deformed one-body oscillator potential can also be described by the $d$-method, without external field and where the dimension can take non-integer values. In this work we first generalize both methods to $N$ particles and any transition between dimensions below $3$. Once this is done, the use of harmonic oscillator interactions between the particles allows complete analytic solutions of both methods, and a direct comparison between them is possible. Assuming that both methods describe the same process, leading to the same ground state energy and wave function, an analytic equivalence between the methods arises. The equivalence between both methods and the validity of the derived analytic relation between them is first tested for two identical bosons and for squeezing transitions from 3 to 2 and 1 dimensions, as well as from 2 to 1 dimension. We also investigate the symmetric squeezing from 3 to 1 dimensions of a system made of three identical bosons. We have in all the cases found that the derived analytic relations between the two methods work very well. This fact permits to relate both methods also for large squeezing scenarios, where the brute force numerical calculation with the external field is too much demanding from the numerical point of view, especially for systems with more than two particles., Comment: To be published in Few-body Systems

We aim to determine the $^{14}$N/$^{15}$N and $^{12}$C/$^{13}$C ratios for HCN in six starless and prestellar cores and compare the results between the direct method using radiative transfer modeling and the indirect double isotope method assuming a fixed $^{12}$C/$^{13}$C ratio. We present IRAM 30m observations of the HCN 1-0, HCN 3-2, HC15N 1-0 and H13CN 1-0 transitions toward six embedded cores. The ${}^{14}$N/${}^{15}$N ratio was derived using both the indirect double isotope method and directly through non-local thermodynamic equilibrium (NLTE) 1D radiative transfer modeling of the HCN emission. The latter also provides the ${}^{12}$C/${}^{13}$C ratio, which we compared to the local interstellar value. The derived ${}^{14}$N/${}^{15}$N ratios using the indirect method are generally in the range of 300-550. This result could suggest an evolutionary trend in the nitrogen fractionation of HCN between starless cores and later stages of the star formation process. However, the direct method reveals lower fractionation ratios of around $\sim$250, mainly resulting from a lower ${}^{12}$C/${}^{13}$C ratio in the range $\sim$20-40, as compared to the local interstellar medium value of 68. This study reveals a significant difference between the nitrogen fractionation ratio in HCN derived using direct and indirect methods. This can influence the interpretation of the chemical evolution and reveal the pitfalls of the indirect double isotope method for fractionation studies. However, the direct method is challenging, as it requires well-constrained source models to produce accurate results. No trend in the nitrogen fractionation of HCN between earlier and later stages of the star formation process is evident when the results of the direct method are considered., Comment: Accepted for publication in A&A

Cyber-physical system sensors emit multivariate time series (MTS) that monitor physical system processes. Such time series generally capture unknown numbers of states, each with a different duration, that correspond to specific conditions, e.g., "walking" or "running" in human-activity monitoring. Unsupervised identification of such states facilitates storage and processing in subsequent data analyses, as well as enhances result interpretability. Existing state-detection proposals face three challenges. First, they introduce substantial computational overhead, rendering them impractical in resourceconstrained or streaming settings. Second, although state-of-the-art (SOTA) proposals employ contrastive learning for representation, insufficient attention to false negatives hampers model convergence and accuracy. Third, SOTA proposals predominantly only emphasize offline non-streaming deployment, we highlight an urgent need to optimize online streaming scenarios. We propose E2Usd that enables efficient-yet-accurate unsupervised MTS state detection. E2Usd exploits a Fast Fourier Transform-based Time Series Compressor (fftCompress) and a Decomposed Dual-view Embedding Module (ddEM) that together encode input MTSs at low computational overhead. Additionally, we propose a False Negative Cancellation Contrastive Learning method (fnccLearning) to counteract the effects of false negatives and to achieve more cluster-friendly embedding spaces. To reduce computational overhead further in streaming settings, we introduce Adaptive Threshold Detection (adaTD). Comprehensive experiments with six baselines and six datasets offer evidence that E2Usd is capable of SOTA accuracy at significantly reduced computational overhead., Comment: Accepted by The Web Conference 2024 (WWW 2024)

Vehicle movement is frequently captured in the form of trajectories, i.e., sequences of timestamped locations. Numerous methods exist that target different tasks involving trajectories such as travel-time estimation, trajectory recovery, and trajectory prediction. However, most methods target only one specific task and cannot be applied universally. Existing efforts to create a universal trajectory model often involve adding prediction modules for adapting to different tasks, while also struggle with incomplete or sparse trajectories. To address these shortcomings, we propose the Universal Vehicle Trajectory Model (UVTM) designed to support different tasks based on incomplete or sparse trajectories without the need for retraining or extra prediction modules. To addresses task adaptability on incomplete trajectories, UVTM divide the spatio-temporal features of trajectories into three distinct domains. Each domain can be masked and generated independently to suit the input and output needs of specific tasks. To handle sparse trajectories effectively, UVTM is pre-trained by reconstructing densely sampled trajectories from sparsely sampled ones, allowing it to extract detailed spatio-temporal information from sparse trajectories. Experiments involving three representative trajectory-related tasks on two real-world vehicle trajectory datasets provide insight into the intended properties performance of UVTM and offer evidence that UVTM is capable of meeting its objectives.

The popularity and diffusion of wearable devices provides new opportunities for sensor-based human activity recognition that leverages deep learning-based algorithms. Although impressive advances have been made, two major challenges remain. First, sensor data is often incomplete or noisy due to sensor placement and other issues as well as data transmission failure, calling for imputation of missing values, which also introduces noise. Second, human activity has multi-scale characteristics. Thus, different groups of people and even the same person may behave differently under different circumstances. To address these challenges, we propose a multilevel heterogeneous neural network, called MHNN, for sensor data analysis. We utilize multilevel discrete wavelet decomposition to extract multi-resolution features from sensor data. This enables distinguishing signals with different frequencies, thereby suppressing noise. As the components resulting from the decomposition are heterogeneous, we equip the proposed model with heterogeneous feature extractors that enable the learning of multi-scale features. Due to the complementarity of these features, we also include a cross aggregation module for enhancing their interactions. An experimental study using seven publicly available datasets offers evidence that MHNN can outperform other cutting-edge models and offers evidence of robustness to missing values and noise. An ablation study confirms the importance of each module., Comment: 14 pages, 7 figures

Spatio-temporal forecasting of future values of spatially correlated time series is important across many cyber-physical systems (CPS). Recent studies offer evidence that the use of graph neural networks to capture latent correlations between time series holds a potential for enhanced forecasting. However, most existing methods rely on pre-defined or self-learning graphs, which are either static or unintentionally dynamic, and thus cannot model the time-varying correlations that exhibit trends and periodicities caused by the regularity of the underlying processes in CPS. To tackle such limitation, we propose Time-aware Graph Structure Learning (TagSL), which extracts time-aware correlations among time series by measuring the interaction of node and time representations in high-dimensional spaces. Notably, we introduce time discrepancy learning that utilizes contrastive learning with distance-based regularization terms to constrain learned spatial correlations to a trend sequence. Additionally, we propose a periodic discriminant function to enable the capture of periodic changes from the state of nodes. Next, we present a Graph Convolution-based Gated Recurrent Unit (GCGRU) that jointly captures spatial and temporal dependencies while learning time-aware and node-specific patterns. Finally, we introduce a unified framework named Time-aware Graph Convolutional Recurrent Network (TGCRN), combining TagSL, and GCGRU in an encoder-decoder architecture for multi-step spatio-temporal forecasting. We report on experiments with TGCRN and popular existing approaches on five real-world datasets, thus providing evidence that TGCRN is capable of advancing the state-of-the-art. We also cover a detailed ablation study and visualization analysis, offering detailed insight into the effectiveness of time-aware structure learning., Comment: published in ICDE 2024

A space-filling curve (SFC) maps points in a multi-dimensional space to one-dimensional points by discretizing the multi-dimensional space into cells and imposing a linear order on the cells. This way, an SFC enables the indexing of multi-dimensional data using a one-dimensional index such as a B+-tree. Choosing an appropriate SFC is crucial, as different SFCs have different effects on query performance. Currently, there are two primary strategies: 1) deterministic schemes, which are computationally efficient but often yield suboptimal query performance, and 2) dynamic schemes, which consider a broad range of candidate SFCs based on cost functions but incur significant computational overhead. Despite these strategies, existing methods cannot efficiently measure the effectiveness of SFCs under heavy query workloads and numerous SFC options. To address this problem, we propose means of constant-time cost estimations that can enhance existing SFC selection algorithms, enabling them to learn more effective SFCs. Additionally, we propose an SFC learning method that leverages reinforcement learning and our cost estimation to choose an SFC pattern efficiently. Experimental studies offer evidence of the effectiveness and efficiency of the proposed means of cost estimation and SFC learning.

Increasing and massive volumes of trajectory data are being accumulated that may serve a variety of applications, such as mining popular routes or identifying ridesharing candidates. As storing and querying massive trajectory data is costly, trajectory simplification techniques have been introduced that intuitively aim to reduce the sizes of trajectories, thus reducing storage and speeding up querying, while preserving as much information as possible. Existing techniques rely mainly on hand-crafted error measures when deciding which point to drop when simplifying a trajectory. While the hope may be that such simplification affects the subsequent usability of the data only minimally, the usability of the simplified data remains largely unexplored. Instead of using error measures that indirectly may to some extent yield simplified trajectories with high usability, we adopt a direct approach to simplification and present the first study of query accuracy driven trajectory simplification, where the direct objective is to achieve a simplified trajectory database that preserves the query accuracy of the original database as much as possible. Specifically, we propose a multi-agent reinforcement learning based solution with two agents working cooperatively to collectively simplify trajectories in a database while optimizing query usability. Extensive experiments on four real-world trajectory datasets show that the solution is capable of consistently outperforming baseline solutions over various query types and dynamics., Comment: This paper has been accepted by ICDE 2024

Sensor data streams occur widely in various real-time applications in the context of the Internet of Things (IoT). However, sensor data streams feature missing values due to factors such as sensor failures, communication errors, or depleted batteries. Missing values can compromise the quality of real-time analytics tasks and downstream applications. Existing imputation methods either make strong assumptions about streams or have low efficiency. In this study, we aim to accurately and efficiently impute missing values in data streams that satisfy only general characteristics in order to benefit real-time applications more widely. First, we propose a message propagation imputation network (MPIN) that is able to recover the missing values of data instances in a time window. We give a theoretical analysis of why MPIN is effective. Second, we present a continuous imputation framework that consists of data update and model update mechanisms to enable MPIN to perform continuous imputation both effectively and efficiently. Extensive experiments on multiple real datasets show that MPIN can outperform the existing data imputers by wide margins and that the continuous imputation framework is efficient and accurate., Comment: Accepted at VLDB 2024

Trajectories that capture object movement have numerous applications, in which similarity computation between trajectories often plays a key role. Traditionally, the similarity between two trajectories is quantified by means of heuristic measures, e.g., Hausdorff or ERP, that operate directly on the trajectories. In contrast, recent studies exploit deep learning to map trajectories to d-dimensional vectors, called embeddings. Then, some distance measure, e.g., Manhattan or Euclidean, is applied to the embeddings to quantify trajectory similarity. The resulting similarities are inaccurate: they only approximate the similarities obtained using the heuristic measures. As distance computation on embeddings is efficient, focus has been on achieving embeddings yielding high accuracy. Adopting an efficiency perspective, we analyze the time complexities of both the heuristic and the learning-based approaches, finding that the time complexities of the former approaches are not necessarily higher. Through extensive experiments on open datasets, we find that, on both CPUs and GPUs, only a few learning-based approaches can deliver the promised higher efficiency, when the embeddings can be pre-computed, while heuristic approaches are more efficient for one-off computations. Among the learning-based approaches, the self-attention-based ones are the fastest to learn embeddings that also yield the highest accuracy for similarity queries. These results have implications for the use of trajectory similarity approaches given different application requirements., Comment: Accepted by VLDB 2024

Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inconsistent or seemingly contradictory performance findings across different studies. This hinders our understanding of the merits of different approaches and slows down progress. We address the need for means of assessing MTS forecasting proposals reliably and fairly, in turn enabling better exploitation of MTS as seen in different applications. Specifically, we first propose BasicTS+, a benchmark designed to enable fair, comprehensive, and reproducible comparison of MTS forecasting solutions. BasicTS+ establishes a unified training pipeline and reasonable settings, enabling an unbiased evaluation. Second, we identify the heterogeneity across different MTS as an important consideration and enable classification of MTS based on their temporal and spatial characteristics. Disregarding this heterogeneity is a prime reason for difficulties in selecting the most promising technical directions. Third, we apply BasicTS+ along with rich datasets to assess the capabilities of more than 45 MTS forecasting solutions. This provides readers with an overall picture of the cutting-edge research on MTS forecasting. The code can be accessed at https://github.com/GestaltCogTeam/BasicTS., Comment: Accepted by TKDE (IEEE Transactions on Knowledge and Data Engineering); The codebase is accessible at: https://github.com/GestaltCogTeam/BasicTS

Movement paths are used widely in intelligent transportation and smart city applications. To serve such applications, path representation learning aims to provide compact representations of paths that enable efficient and accurate operations when used for different downstream tasks such as path ranking and travel cost estimation. In many cases, it is attractive that the path representation learning is lightweight and scalable; in resource-limited environments and under green computing limitations, it is essential. Yet, existing path representation learning studies focus on accuracy and pay at most secondary attention to resource consumption and scalability. We propose a lightweight and scalable path representation learning framework, termed LightPath, that aims to reduce resource consumption and achieve scalability without affecting accuracy, thus enabling broader applicability. More specifically, we first propose a sparse auto-encoder that ensures that the framework achieves good scalability with respect to path length. Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders. We also propose global-local knowledge distillation to further reduce the size and improve the performance of sparse path encoders. Finally, we report extensive experiments on two real-world datasets to offer insight into the efficiency, scalability, and effectiveness of the proposed framework., Comment: This paper has been accepted by ACM SIGKDD-23

Given an origin (O), a destination (D), and a departure time (T), an Origin-Destination (OD) travel time oracle~(ODT-Oracle) returns an estimate of the time it takes to travel from O to D when departing at T. ODT-Oracles serve important purposes in map-based services. To enable the construction of such oracles, we provide a travel-time estimation (TTE) solution that leverages historical trajectories to estimate time-varying travel times for OD pairs. The problem is complicated by the fact that multiple historical trajectories with different travel times may connect an OD pair, while trajectories may vary from one another. To solve the problem, it is crucial to remove outlier trajectories when doing travel time estimation for future queries. We propose a novel, two-stage framework called Diffusion-based Origin-destination Travel Time Estimation (DOT), that solves the problem. First, DOT employs a conditioned Pixelated Trajectories (PiT) denoiser that enables building a diffusion-based PiT inference process by learning correlations between OD pairs and historical trajectories. Specifically, given an OD pair and a departure time, we aim to infer a PiT. Next, DOT encompasses a Masked Vision Transformer~(MViT) that effectively and efficiently estimates a travel time based on the inferred PiT. We report on extensive experiments on two real-world datasets that offer evidence that DOT is capable of outperforming baseline methods in terms of accuracy, scalability, and explainability., Comment: 15 pages, 12 figures, accepted by SIGMOD International Conference on Management of Data 2024

Pre-stellar cores represent the earliest stage of the star- and planet-formation process. By characterizing the physical and chemical structure of these cores we can establish the initial conditions for star and planet formation and determine to what degree the chemical composition of pre-stellar cores is inherited to the later stages. A 3D MHD model of a pre-stellar core embedded in a dynamic star-forming cloud is post-processed using sequentially continuum radiative transfer, a gas-grain chemical model, and a line-radiative transfer model. Results are analyzed and compared to observations of CH$_3$OH and $c$-C$_3$H$_2$ in L1544. Nine different chemical models are compared to the observations to determine which initial conditions are compatible with the observed chemical segregation in the prototypical pre-stellar core L1544. The model is able to reproduce several aspects of the observed chemical differentiation in L1544. Extended methanol emission is shifted towards colder and more shielded regions of the core envelope while $c$-C$_3$H$_2$ emission overlaps with the dust continuum, consistent with the observed chemical structure. Increasing the strength of the interstellar radiation field or the cosmic-ray ionization rate with respect to the typical values assumed in nearby star-forming regions leads to synthetic maps that are inconsistent with the observed chemical structure. Our model shows that the observed chemical dichotomy in L1544 can arise as a result of uneven illumination due to the asymmetrical structure of the 3D core and the environment within which the core has formed. This highlights the importance of the 3D structure at the core-cloud transition on the chemistry of pre-stellar cores., Comment: Accepted for publication in A&A

Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data. To such learning, we propose a contrastive hypergraph neural network, CHGNN, that exploits self-supervised contrastive learning techniques to learn from labeled and unlabeled data. First, CHGNN includes an adaptive hypergraph view generator that adopts an auto-augmentation strategy and learns a perturbed probability distribution of minimal sufficient views. Second, CHGNN encompasses an improved hypergraph encoder that considers hyperedge homogeneity to fuse information effectively. Third, CHGNN is equipped with a joint loss function that combines a similarity loss for the view generator, a node classification loss, and a hyperedge homogeneity loss to inject supervision signals. It also includes basic and cross-validation contrastive losses, associated with an enhanced contrastive loss training process. Experimental results on nine real datasets offer insight into the effectiveness of CHGNN, showing that it outperforms 13 competitors in terms of classification accuracy consistently., Comment: Accepted by TKDE

MHD models and the observation of accretion streamers confirmed that protostars can undergo late accretion events after the initial collapse phase. To provide better constraints, we study the evolution of stellar masses in MHD simulations of a (4 pc)^3 molecular cloud. Tracer particles allow us to accurately follow the trajectory of accreting material for all protostars and thereby constrain the accretion reservoir of the stars. The diversity of the accretion process implies that stars in the solar mass regime can have vastly different accretion histories. Some stars accrete most of their mass during the initial collapse phase, while others gain >50 % of their final mass from late infall. The angular momentum budget of stars that experience substantial infall, so-called late accretors, is significantly higher than for stars without or with only little late accretion. As the probability of late infall increases with increasing final stellar mass, the specific angular momentum budget of higher mass stars is on average higher. The hypothetical centrifugal radius computed from the accreting particles at the time of formation is orders of magnitude higher than observed disk sizes, which emphasizes the importance of angular momentum transport during disk formation. Nevertheless, we find a correlation that the centrifugal radius is highest for stars with substantial infall, which suggests that very large disks are the result of recent infall events. There are also indications for a subtle trend of increasing centrifugal radius with increasing final stellar mass, which is in agreement with an observed marginal correlation of disk size and stellar mass. Finally, we show that late accretors become embedded again during infall. As a consequence, late accretors are (apparently) rejuvenated and would be classified as Class 0 objects according to their bolometric temperature despite being 1 Myr old., Comment: 18 pages, 7 figures, accepted invited paper for EpJ Plus Focus Point on Environmental and multiplicity effects on planet formation

The purpose of this paper is to show that, by combining Feshbach resonances with external confining potentials, the energy scale factor of neighboring Efimov states can be tremendously reduced. The Efimov conditions can be reached for systems made of three different particles. For the case of two identical light particles and a heavy particle the energy factor can be reduced by many orders of magnitude, and the Efimov states are in this way more easily reachable experimentally. The equivalence between external potentials and the formulation in terms of non-integer dimensions, $d$, is exploited. The technically simpler $d$-method is used to derive analytic expressions for two-component relative wave functions describing two short-range square-well interacting particles. The two components express one open and one closed channel. The scattering length is obtained after phase shift expansion, providing an analytic form for the Efimov condition. We illustrate the results by means of systems made of $^7$Li, $^{39}$K, and $^{87}$Rb, with realistic parameters. The related pairs of dimension and magnetic field are shown and discussed. The results are universal as they only rely on large-distance properties., Comment: To be published in the European Physical Journal D

Indoor location-based services rely on the availability of sufficiently accurate positioning in indoor spaces. A popular approach to positioning relies on so-called radio maps that contain pairs of a vector of Wi-Fi signal strength indicator values (RSSIs), called a fingerprint, and a location label, called a reference point (RP), in which the fingerprint was observed. The positioning accuracy depends on the quality of the radio maps and their fingerprints. Radio maps are often sparse, with many pairs containing vectors missing many RSSIs as well as RPs. Aiming to improve positioning accuracy, we present a complete set of techniques to impute such missing values in radio maps. We differentiate two types of missing RSSIs: missing not at random (MNAR) and missing at random (MAR). Specifically, we design a framework encompassing a missing RSSI differentiator followed by a data imputer for missing values. The differentiator identifies MARs and MNARs via clustering-based fingerprint analysis. Missing RSSIs and RPs are then imputed jointly by means of a novel encoder-decoder architecture that leverages temporal dependencies in data collection as well as correlations among fingerprints and RPs. A time-lag mechanism is used to consider the aging of data, and a sparsity-friendly attention mechanism is used to focus attention score calculation on observed data. Extensive experiments with real data from two buildings show that our proposal outperforms the alternatives with significant advantages in terms of imputation accuracy and indoor positioning accuracy., Comment: Accepted at ICDE 2023

Due to the sweeping digitalization of processes, increasingly vast amounts of time series data are being produced. Accurate classification of such time series facilitates decision making in multiple domains. State-of-the-art classification accuracy is often achieved by ensemble learning where results are synthesized from multiple base models. This characteristic implies that ensemble learning needs substantial computing resources, preventing their use in resource-limited environments, such as in edge devices. To extend the applicability of ensemble learning, we propose the LightTS framework that compresses large ensembles into lightweight models while ensuring competitive accuracy. First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model. Second, we propose means of identifying Pareto optimal settings w.r.t. model accuracy and model size, thus enabling users with a space budget to select the most accurate lightweight model. We report on experiments using 128 real-world time series sets and different types of base models that justify key decisions in the design of LightTS and provide evidence that LightTS is able to outperform competitors., Comment: 15 pages. An extended version of "LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation" accepted at SIGMOD 2023

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting. However, while models have become increasingly complex and computationally intensive, they struggle to improve accuracy. Pursuing a different direction, this study aims instead to enable much more efficient, lightweight models that preserve accuracy while being able to be deployed on resource-constrained devices. To achieve this goal, we characterize popular CTS forecasting models and yield two observations that indicate directions for lightweight CTS forecasting. On this basis, we propose the LightCTS framework that adopts plain stacking of temporal and spatial operators instead of alternate stacking that is much more computationally expensive. Moreover, LightCTS features light temporal and spatial operator modules, called L-TCN and GL-Former, that offer improved computational efficiency without compromising their feature extraction capabilities. LightCTS also encompasses a last-shot compression scheme to reduce redundant temporal features and speed up subsequent computations. Experiments with single-step and multi-step forecasting benchmark datasets show that LightCTS is capable of nearly state-of-the-art accuracy at much reduced computational and storage overheads., Comment: accepted by ACM SIGMOD 2023

A novel practical few-body method is formulated to include isospin symmetry for nuclear halo structures. The method is designed to describe beta decay, where the basic concept of isospin symmetry facilitates a proper understanding. Both isobaric analogue and anti-analogue states are treated. We derive general and explicit formulas for three-body systems using hyperspherical coordinates. The example of the beta decaying $^{11}$Li ($^{9}$Li+$n$+$n$) is chosen as a challenging application for numerical calculations of practical interest. The detailed results are compared to existing experimental data and good agreement is found at high excitation energies, where the isobaric analogue and anti-analogue states are situated in the daughter nucleus. An interpretation of the decay pattern at lower excitation energies is suggested. Decays of the $^{9}$Li-core and the two halo-neutrons are individually treated and combined to the daughter system with almost unique isospin, which we predict to be broken by about $0.4\%$ probability. Properties of decay products are predicted as possible future tests of this model., Comment: To be published in Physical Review C