Accurate spatio-temporal traffic prediction is essential for optimizing urban traffic management and resource allocation. To reduce the cost and complexity of cross-city deployment, recent studies have explored spatio-temporal foundation models capable of accurate zero-shot prediction. However, these models are limited to single-modal data, which restricts their capacity to capture the complexity of real-world traffic dynamics. The increasing availability of multi-modality data—such as satellite imagery and points of interest (POI)—offers a promising avenue for enhancing cross-city traffic prediction by providing richer background contexts. Despite this potential, developing foundational models for multi-modality spatio-temporal prediction presents two challenges: the availability and quality of multi-modality data vary significantly across cities, with some cities lacking certain modalities or containing noisy information; and spatial patterns are highly localized and specific to individual regions, which hinders generalization. To address these challenges, we propose MoST, a foundation model for multi-modality spatio-temporal traffic prediction. We introduce a Multi-modality Refinement Module that encodes available modality data and adaptively selects task-relevant modalities while suppressing noisy modalities. Furthermore, we design a Spatio-Temporal Prediction Module that incorporates a spatial expert selection mechanism guided by multi-modality cues. This mechanism dynamically identifies region-specific spatial patterns and assigns appropriate spatial experts to model local dependencies. Finally, we conduct extensive experiments on real-world datasets to validate the superior performance and strong generalization capability of MoST.

Accurate prediction of waterlogging depth (WD) is a critical task for urban emergency management and smart-city development. Traditional hydrological forecasting models rely heavily on high-precision weather and terrain data, and struggle to adapt to dynamic rainfall patterns. Recently, deep learning-based methods have shown promising results in capturing complex dynamic patterns. However, these data-driven models face challenges in modeling hydrological mechanisms and effectively fusing multimodal data. To address these limitations, we propose Waterlogformer, a multimodal model for WD prediction. Waterlogformer employs a dual-branch architecture to jointly model WD and rainfall time series alongside static geospatial features. It computes cumulative rainfall based on terrain to incorporate water flow accumulation mechanisms, thereby effectively capturing the impact of rainfall on WD. Furthermore, a Multimodal Fusion Prediction Module fuses multimodal data, enhanced by spatial contrastive learning to improve the model's understanding of geographic relationships. Experiment results on a real-world dataset demonstrate the superior performance of Waterlogformer. The source code is available at https://github.com/decisionintelligence/Waterlogformer.

Time series anomaly detection is typically used to identify data that deviates significantly from normal data, often indicating faults or failures in the underlying system, thus facilitating system stability and safety. Most existing methods focus on detecting anomalies after they occur, while research on predicting future anomalies remains scarce. Before anomalies manifest themselves, there are often subtle precursors exhibiting slight deviations from normal behavior, with varying reaction times and intensities. Next, the setting is often characterized by a lack of labeled data, which complicates model training. To address these challenges, we propose a time series anomaly prediction framework, TAP. It can adapt flexibly to varying reaction times of anomaly precursors across different variables using a period-aware multi-scale module, and it is able to strengthen the distinction between precursors and normal sequences via a dual-branch framework that combines reconstruction and contrastive learning. The contrastive branch employs a controlled generation strategy within the multi-scale patching to produce diverse hard negative samples for precursor identification. The reconstruction branch complements this by evaluating fluctuation magnitudes to ensure sensitivity to subtle variations. We report on experiments on eight datasets from diverse domains, finding that TAP is capable of competitive or superior performance compared to baseline methods for both anomaly detection and prediction.

With the proliferation of GPS-equipped edge devices, huge trajectory data are generated and accumulated in various domains, driving numerous urban applications. However, due to the limited data acquisition capabilities of edge devices, many trajectories are often recorded at low sampling rates, reducing the effectiveness of these applications. To address this issue, we aim to recover high-sample-rate trajectories from low-sample-rate ones enhancing the usability of trajectory data. Recent approaches to trajectory recovery often assume centralized data storage, which can lead to catastrophic forgetting, where previously learned knowledge is entirely forgotten when new data arrives. This not only poses privacy risks but also degrades performance in decentralized settings where data streams into the system incrementally. To enable decentralized training and streaming trajectory recovery, we propose aLightweight incremental framework for federatedTrajectoryRecovery, called LightTR+, which is based on a client-server architecture. Given the limited processing capabilities of edge devices, LightTR+ includes a lightweight local trajectory embedding module that enhances computational efficiency without compromising feature extraction capabilities. To mitigate catastrophic forgetting, we propose an intra-domain knowledge distillation module. Additionally, LightTR+ features a meta-knowledge enhanced local-global training scheme, which reduces communication costs between the server and clients, further improving efficiency. Extensive experiments offer insight into the effectiveness and efficiency of LightTR+.

In the field of material science, the analysis of the properties of crystalline materials is of key importance. Recently, machine learning has become a prominent tool for predicting the properties of materials based on their structure. However, the application of machine learning to crystal property prediction faces two significant challenges. The first is the scarcity of labeled data, due to the time-consuming and resource-intensive process of crystal property labeling. The second is the importance of leveraging specialized knowledge when performing crystal structure analysis, which requires adapting machine learning methods specifically for the crystal domain. In this paper, we propose a new semi-supervised framework, aKnowledge-BasedSemi-Supervised crystal property prediction (KBSS) framework, which employs consistency regularization to leverage both labeled and unlabeled data while incorporating crystal knowledge guidance. Specifically, to use unlabeled data efficiently, the KBSS framework incorporates two key modules: a knowledge-guided augmentation (KGA) module and an adaptive pseudo-label filtering (APF) module. The KGA module utilizes the Monte Carlo method to leverage knowledge from the crystal domain to guide weak and strong augmentations of crystal structures. The APF module enhances the pseudo-labeling process for unlabeled crystal data by enabling task-guided uncertainty adjustment and category-aware pseudo-label selection. The experimental results show that KBSS achieves state-of-the-art performance. All code is publicly available athttps://github.com/HaominYu0/KBSS.

The financial market plays a crucial role in the modern economy by influencing capital allocation, corporate valuation, and investor behavior. However, its complex dependencies and non-stationary dynamics present significant challenges for financial stock prediction. Previous predictive approaches are typically categorized into Univariate Time Series (UTS) and Multivariate Time Series (MTS) paradigms. UTS methods overlook both cross-feature and cross-stock influences, while MTS methods can only capture one of these simultaneously. Although some recent approaches claim to model 3D Multivariate Time Series (3D-MTS) dependencies, they often discard substantial information and fail to capture the dynamics of the stock market. To address these limitations, we propose FinD3, a Financial 3D model using Dual cubic state spaces and Dynamic hypergraphs. To extract the inherent complex relationships in 3D-MTS, we propose a novel Dual Cubic State Space Model (DCSSM) to capture both cross-feature and cross-stock patterns. Furthermore, to more accurately reflect the dynamics of the stock market, we present an Evolving Hypergraph Attention (EHA) module, which captures dynamic changes in financial markets and updates the hypergraph based on a priori hypergraph. Experimental results demonstrate that FinD3 achieves state-of-the-art performance in quantitative trading performance on two real-world stock market datasets, offering a promising solution to practical quantitative trading challenges. The code is available at: https://github.com/decisionintelligence/FinD3.

Accurate land deformation prediction using InSAR (Interferometric Synthetic Aperture Radar) technology is crucial for early warning of geological disasters. However, existing prediction methods face two major challenges: cross-area association bottleneck and inadequate handling of temporal distribution heterogeneity. To address these challenges, we propose Multi-modal Adaptive Association Learning framework (MAAL). For the spatial knowledge transfer challenge, we introduce a cross-area multi-modal association learning module that integrates multi-modal (InSAR and geological text) data to enable knowledge transfer between areas with similar geological characteristics. For temporal distribution heterogeneity, we develop an adaptive evolution stage recognition module that uses distribution routers to identify different temporal patterns, then applies corresponding linear extractors to model the heterogeneous landslide evolution. Experimental validation on 889 hazardous areas demonstrates that MAAL outperforms baselines.

Time series classification (TSC) is an important task in time series analysis. Existing TSC methods mainly train on each single domain separately, suffering from a degradation in accuracy when the samples for training are insufficient in certain domains. The pre-training and fine-tuning paradigm provides a promising direction for solving this problem. However, time series from different domains are substantially divergent, which challenges the effective pre-training on multi-source data and the generalization ability of pre-trained models. To handle this issue, we introduce Augmented Series and Image Contrastive Learning for Time Series Classification (AimTS), a pre-training framework that learns generalizable representations from multi-source time series data. We propose a two-level prototype-based contrastive learning method to effectively utilize various augmentations in multi-source pre-training, which learns representations for TSC that can be generalized to different domains. In addition, considering augmentations within the single time series modality are insufficient to fully address classification problems with distribution shift, we introduce the image modality to supplement structural information and establish a series-image contrastive learning to improve the generalization of the learned representations for TSC tasks. Extensive experiments show that after multi-source pre-training, AimTS achieves good generalization performance, enabling efficient learning and even few-shot learning on various downstream TSC datasets.

Recent research in Text-to-SQL translation has primarily adopted in-context learning methods leveraging large language models (LLMs), achieving significant progress. However, these methods face challenges in adapting to natural language questions of varying difficulty and the relevance of the few-shot examples provided. In this paper, we propose an adaptive in-context learning approach with difficulty-aware instruction and retrieval-augmented generation to enhance the performance of Text-to-SQL translation (AID-SQL). First, we introduce adaptive instructions for LLMs, which employ precise difficulty classification to apply difficulty-adaptive generative guidelines and chain of thought (CoT) templates for varying difficulty levels. We automatically incorporate few-shot examples retrieved through the knowledge base into the CoT template to construct CoT-enhanced examples, which improves the capability of LLMs with retrieval-augmented generation (RAG). Furthermore, considering that current RAG methods struggle to effectively measure the contribution of retrieved examples in solving the specific task of Text-to-SQL translation, we train a ranking model that can better bridge the semantic and structural gap between NL questions and SQL queries. This approach can better understand semantic information and allows for retrieving examples that are more beneficial to the final problem-solving. We evaluate our method on five benchmarks. Our method achieves competitive performance compared with existing methods.

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 EasyTime11https://decisionintelligence.github.io/EasyTime, we aim to show how it simplifies the use of time-series forecasting and facilitates the development of new generations of time series forecasting methods.

Time series data captures properties that change over time. Such data occurs widely, ranging from the scientific and medical domains to the industrial and environmental domains. When the properties in time series exhibit spatial variations, we often call the data spatio-temporal. As part of the continued digitalization of processes throughout society, increasingly large volumes of time series and spatio-temporal data are available. In this tutorial, we focus on data-driven decision making with such data, e.g., enabling greener and more efficient transportation based on traffic time series forecasting. The tutorial adopts the holistic paradigm of “data-governance-analytics-decision.” We first introduce the data foundation of time series and spatio-temporal data, which is often heterogeneous. Next, we discuss data governance methods that aim to improve data quality. We then cover data analytics, focusing on five desired characteristics: automation, robustness, generality, explainability, and resource efficiency. We finally cover data-driven decision making strategies and briefly discuss promising research directions. We hope that the tutorial will serve as a primary resource for researchers and practitioners who are interested in value creation from time series and spatio-temporal data.

Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they predominantly focus on the topological structures from single modality data, i.e., road networks, overlooking the geometric and contextual features associated with path-related images, e.g., remote sensing images. Similar to human understanding, integrating information from multiple modalities can provide a more comprehensive view, enhancing both representation accuracy and generalization. However, variations in information granularity impede the semantic alignment of road network-based paths (road paths) and image-based paths (image paths), while the heterogeneity of multi-modal data poses substantial challenges for effective fusion and utilization. In this paper, we propose a novel Multi-modal, Multi-granularity Path Representation Learning Framework (MM-Path), which can learn a generic path representation by integrating modalities from both road paths and image paths. To enhance the alignment of multi-modal data, we develop a multi-granularity alignment strategy that systematically associates nodes, road sub-paths, and road paths with their corresponding image patches, ensuring the synchronization of both detailed local information and broader global contexts. To address the heterogeneity of multi-modal data effectively, we introduce a graph-based cross-modal residual fusion component designed to comprehensively fuse information across different modalities and granularities. Finally, we conduct extensive experiments on two large-scale real-world datasets under two downstream tasks, validating the effectiveness of the proposed MM-Path.

We study the problem of time series anomaly prediction, which is relevant to a range of real-world applications. Existing anomaly prediction methods rely on labeled training data for achieving acceptable accuracy. However, such data may be difficult to obtain; and in real-time deployments, anomalies can occur that were not seen in labeled data, thus making them difficult to predict. We provide a theoretical analysis and propose an Importance-based Generative Contrastive Learning method (IGCL) for unsupervised anomaly prediction. IGCL employs a controlled diffusion module to produce anomaly precursor patterns. Next, ICGL learns contextual representations to extract temporal dependencies from pairs of normal time series and anomaly precursors. IGCL is then able to predict anomalies by identifying anomaly precursors that will evolve into future anomalies. To address challenges caused by potentially complex precursor combinations involving multiple variables, we propose a memory bank with importance scores that stores representative samples adaptively and generates more complex anomaly precursors. Extensive experiments on nine benchmark datasets offer evidence that the proposed method is able to outperform state-of-the-art baselines.

Time Series Forecasting (TSF) is key functionality in numerous fields, such as financial investment, weather services, and energy management. Although increasingly capable TSF methods occur, many of them require domain-specific data collection and model training and do not generalize well when applied in other domains. Time Series Foundation Models (TSFMs) that are pre-trained on massive heterogeneous time series data aim to overcome these limitations. The prospects for generalizability have spurred the development of a new generation of TSFMs. This study proposes a benchmark, TSFM-Bench, to facilitate comprehensive and unified evaluation of TSFMs. TSFM-Bench covers a wide range of TSFMs, including those based on large language models and those pre-trained on time series data. TSFM-Bench supports multiple forecasting scenarios, including zero-shot, few-shot, and full-shot, enabling assessment across the full range of adaptation strategies. TSFM-Bench also provides a standardized experimental protocols for critical evaluation processes such as dataset splitting, loading, normalization, and few-shot sampling, facilitating consistency and fairness. We report on an extensive evaluation of TSFMs across a diverse range of datasets spanning multiple domains and exhibiting varied statistical characteristics. Specifically, we identify pros and cons and inherent limitations of existing TSFMs, and we propose potential directions for new model designs.

Multivariate time series forecasting is crucial for various applications, such as financial investment, energy management, weather forecasting, and traffic optimization. However, accurate forecasting is challenging due to two main factors. First, real-world time series often show heterogeneous temporal patterns caused by distribution shifts over time. Second, correlations among channels are complex and intertwined, making it hard to model the interactions among channels precisely and flexibly.

Spatio-temporal data are foundational to understanding and modeling dynamic real-world phenomena such as human mobility, traffic flow, epidemic spread, and urban dynamics.With the growing availability of location-aware web data and the rise of intelligent urban infrastructures, analyzing spatio-temporal patterns has become both highly valuable and technically challenging.This tutorial provides a comprehensive overview of spatio-temporal data analytics, unifying perspectives from data management, research methodology, and emerging foundation models.We begin with a review of spatio-temporal data management systems, introducing the core data models, spatial-temporal indexing techniques, and scalable architectures for storing and querying large-scale mobility data.We then delve into trajectory learning, covering methods for prediction, generation, and reconstruction of movement sequences at the individual level.Next, we explore spatio-temporal graph learning, which focuses on forecasting region-level dynamics using dynamic graph neural networks.Multi-region, multi-task, and multi-domain spatio-temporal learning will be identified and introduced in detail.Finally, we present advanced learning frameworks that integrate federated learning, continual learning, and LLM-based approaches to build privacy-preserving, scalable, and adaptive spatio-temporal models.Through the lens of recent methodological and systemlevel advances, this tutorial bridges algorithmic design and practical deployment of spatio-temporal learning systems.It is suitable for researchers and practitioners working in machine learning, data mining, geospatial analysis, and intelligent systems.

Time series anomaly detection (TSAD) plays an important role in many domains such as finance, transportation, and healthcare. With the ongoing instrumentation of reality, more time series data will be available, leading also to growing demands for TSAD. While many TSAD methods already exist, new and better methods are still desirable. However, effective progress hinges on the availability of reliable means of evaluating new methods and comparing them with existing methods. We address deficiencies in current evaluation procedures related to datasets and experimental settings and protocols. Specifically, we propose a new time series anomaly detection benchmark, called TAB. First, TAB encompasses 29 public multivariate datasets and 1,635 univariate time series from different domains to facilitate more comprehensive evaluations on diverse datasets. Second, TAB covers a variety of TSAD methods, including Non-learning, Machine learning, Deep learning, LLM-based, and Time-series pre-trained methods. Third, TAB features a unified and automated evaluation pipeline that enables fair and easy evaluation of TSAD methods. Finally, we employ TAB to evaluate existing TSAD methods and report on the outcomes, thereby offering a deeper insight into the performance of these methods.

Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns.

The widespread deployment of wireless and mobile devices results in a proliferation of decentralized spatio-temporal data. Many recent proposals that target deep learning for spatio-temporal prediction assume that all data is available at a central location and suffers from so-called catastrophic forgetting, where previously learned knowledge is entirely forgotten when new data arrives. Such proposals may face data privacy concerns and may experience deteriorating prediction performance when applied in decentralized settings where data streams into the system. To bridge the gap between decentralized training and spatio-temporal prediction on streaming data, we propose a unified federated continuous learning framework, which uses a horizontal federated learning mechanism for protecting data privacy and includes a global replay buffer with synthetic spatio-temporal data generated by the previously learned global model. For each client, we fuse the current training data with synthetic spatio-temporal data using a spatio-temporal mixup mechanism to preserve historical knowledge effectively, thus avoiding catastrophic forgetting. To enable holistic representation preservation, the local models at clients each integrates a general spatio-temporal autoencoder with a spatio-temporal simple siamese network that aims to ensure prediction accuracy and avoid holistic feature loss. Extensive experiments on real data offer insight into the effectiveness of the proposed framework.

Significant wave height (SWH) is a vital metric in marine science, and accurate SWH estimation is crucial for various applications, e.g., marine energy development, fishery, early warning systems for potential risks, etc. Traditional SWH estimation methods that are based on numerical models and physical theories are hindered by computational inefficiencies. Recently, machine learning has emerged as an appealing alternative to improve accuracy and reduce computational time. However, due to limited observational technology and high costs, the scarcity of real-world data restricts the potential of machine learning models. To overcome these limitations, we propose an ocean SWH estimation framework, namely Orca. Specifically, Orca enhances the limited spatio-temporal reasoning abilities of classic LLMs with a novel spatiotemporal aware encoding module. By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data. Experimental results on the Gulf of Mexico demonstrate that Orca achieves state-of-the-art performance in SWH estimation.

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.

The unprecedented availability of new types of data coupled with the invention of new technologies combine to enable entirely new or higher-resolution services that in turn enable more rational and data-driven processes. We consider the overall process of vehicular transportation and, more specifically, the process of deciding which route to follow when having to reach a destination. Early solutions modeled a road work as a graph, used sparse in-road sensor data to assign weights to graph edges, and then applied improved versions of Dijkstra's algorithm to find routes with the lowest sums of edge weights. Since then, massive vehicle trajectory data has become available. When coupled with new technologies, this data enables entirely new and higher-resolution routing services that in turn enable better routing. For more than a decade, the authors have engaged in research aimed at exploiting trajectory data to enable better routing. The resulting technologies were developed outside a DBMS. Here, we cover aspects of this research. Further, we challenge the community to develop DBMS support for these and other aspects of routing.

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, e.g., for classification, 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 with the 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 with the original training data. The first difficulty in enabling continual calibration on the edge is that the full training data may be too large and thus cannot be assumed to be 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.

Accurate long-term forecasting from multivariate time series has important real-world applications. However, achieving this so is challenging. Thus, analyses reveal that time series that span long durations often exhibit dynamic and disrupted correlations. State-of-the-art methods employ attention mechanisms to capture dynamic correlations, but they often do not contend well with disrupted correlations, which reduces prediction accuracy. We introduce local and global information concepts and then leverage these in a Memory Guided Transformer, called the Memformer. By integrating patch-wise recurrent graph learning and global attention, the Memformer aims to capture dynamic correlations and take disrupted correlations into account. We also integrate a so-called Alternating Memory Enhancer into the Memformer to capture correlations between local and global information. We report on experiments that offer insight into the effectiveness of the Memformer at capturing dynamic correlations and its robustness to disrupted correlations. The experiments offer evidence that the new method is capable of advancing the state-of-the-art in forecasting accuracy on real-world datasets.

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 noncompetitive 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.

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.

With the continued migration of storage to cloud database systems, the impact of slow queries in such systems on services and user experience is increasing. Root-cause diagnosis plays an indispensable role in facilitating slow-query detection and revision. This paper proposes a method capable of both identifying possible root cause types for slow queries and ranking these according to their potential for accelerating slow queries. This enables prioritizing root causes with the highest impact, in turn improving slow-query revision effectiveness. To enable more accurate and detailed diagnoses, we propose the multimodal Ranking for the Root Causes of slow queries (RCRank) framework, which formulates root cause analysis as a multimodal machine learning problem and leverages multimodal information from query statements, execution plans, execution logs, and key performance indicators. To obtain expressive embeddings from its heterogeneous multimodal input, RCRank integrates self-supervised pre-training that enhances cross-modal alignment and task relevance. Next, the framework integrates root-cause-adaptive cross Transformers that enable adaptive fusion of multimodal features with varying characteristics. Finally, the framework offers a unified model that features an impact-aware training objective for identifying and ranking root causes. We report on experiments on real and synthetic datasets, finding that RCRank is capable of consistently outperforming the state-of-the-art methods at root cause identification and ranking according to a range of metrics.

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 results offer a deeper understanding of the forecasting methods, allowing us to better select the ones that are most suitable for particular datasets and settings. Overall, TFB and this evaluation provide researchers with improved means of designing new TSF methods.

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.

Flink clusters often suffer from hotspot issues where the monitored job delay and CPU usage keep rising and remain high. This necessitates the detection of anomalous time series to pinpoint the hotspot machines. However, the state-of-the-art unsupervised time series anomaly detection (UTAD) methods are ineffective in this scenario. We identify two main reasons for this. First, the hotspot scenario requires us to pay particular attention to Flink-specific anomalies, e.g., slow-rising and high-level anomalies, which the existing methods struggle to address. Second, the state-of-the-art anomaly detection methods often assume that training datasets do not contain anomalies, but the data collected from the running Flink clusters contains noise, which causes these methods to learn anomalous patterns as normal patterns. In this paper, we first conduct experiments to analyze why existing methods fail in the Flink scenario. To tackle these challenges, we propose a cross-contrastive approach to learn the context information for each timestamp to enable Flink-specific anomaly detection. Then, to address noisy anomalies, we incorporate prior knowledge to set an anomaly boundary to prevent the model from learning anomalous patterns. Extensive experiments show that our method not only outperforms existing methods in the Flink scenario but also achieves state-of-the-art results on public benchmark datasets.

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.

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.

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approaches. However, automated CTS solutions remain in their infancy and are only able to find optimal architectures for predefined hyperparameters and scale poorly to large-scale CTS. To overcome these limitations, we propose AutoCTS+, a joint, scalable framework, to automatically devise effective CTS forecasting models. Specifically, we encode each candidate architecture and accompanying hyperparameters into a joint graph representation. We introduce an efficient Architecture-Hyperparameter Comparator (AHC) to rank all architecture-hyperparameter pairs, and we then further evaluate the top-ranked pairs to select an architecture-hyperparameter pair as the final model. Extensive experiments on six benchmark datasets demonstrate that AutoCTS+ not only eliminates manual efforts but also is capable of better performance than manually designed and existing automatically designed CTS models. In addition, it shows excellent scalability to large CTS.

Robust multivariate time series forecasting is crucial in many cyberphysical and Internet of Things applications. Existing state-of-the-art robust forecasting models decompose time series into independent functions covering trends and periodicities. However, these independent functions fail to capture correlations among multiple time series, thereby reducing prediction accuracy. Moreover, existing robust forecasting models treat certain abrupt but normal changes, e.g., caused by holidays, as outliers because they occur infrequently and have data distributions that resemble those of outliers. This exacerbates model bias and reduces prediction accuracy. This paper aims to capture correlations across multiple time series and abrupt but normal changes, thereby improving prediction accuracy. We employ weak labels to partition the dataset into source and target domains. Then, we propose the Domain Adversarial Robust Forecaster (DARF). This forecasting model is based on adversarial domain adaptation and includes two novel modules: Correlated Robust Forecaster (CORF) and Domain Critic. Specifically, CORF constitutes an encoder-decoder framework proficient at robust multivariate time series forecasting, and Domain Critic works to reduce data bias. Extensive experiments and discussions show that DARF is capable of state-of-the-art forecasting accuracy.

Predictive autoscaling is a key enabler for optimizing cloud resource allocation in Alibaba Cloud's computing platforms, which dynamically adjust the Elastic Compute Service (ECS) instances based on predicted user demands to ensure Quality of Service (QoS). However, user demands in the cloud are often highly complex, with high uncertainty and scale-sensitive temporal dependencies, thus posing great challenges for accurate prediction of future demands. These in turn make autoscaling challenging---autoscaling needs to properly account for demand uncertainty while maintaining a reasonable trade-off between two contradictory factors, i.e., low instance running costs vs. low QoS violation risks. To address the above challenges, we propose a novel predictive autoscaling framework MagicScaler , consisting of a Multi-scale attentive Gaussian process based predictor and an uncertainty-aware scaler. First, the predictor carefully bridges the best of two successful prediction methodologies---multi-scale attention mechanisms, which are good at capturing complex, multi-scale features, and stochastic process regression, which can quantify prediction uncertainty, thus achieving accurate demand prediction with quantified uncertainty. Second, the scaler takes the quantified future demand uncertainty into a judiciously designed loss function with stochastic constraints, enabling flexible trade-off between running costs and QoS violation risks. Extensive experiments on three clusters of Alibaba Cloud in different Chinese cities demonstrate the effectiveness and efficiency of MagicScaler , which outperforms other commonly adopted scalers, thus justifying our design choices.

Multiple time series forecasting plays an essential role in many applications. Solutions based on graph neural network (GNN) that deliver state-of-the-art forecasting performance use the relation graph which can capture historical correlations among time series. However, in real world, it is common that correlations among time series evolve across time, resulting in dynamic relation graph, where the future correlations may be different from those in history. To address this problem, we propose multiple time series forecasting with dynamic graph modeling (MTSF-DG) that is able to learn historical relation graphs and predicting future relation graphs to capture the dynamic correlations. We also propose a causal GNN to extract features from both kinds of relation graphs efficiently. Then we propose a reasoning network to explicitly learn the variant influence from historical timestamps to future timestamps for final forecasting. Extensive experiments on six benchmark datasets show that MTSF-DG consistently outperforms state-of-the-art baselines, and justify our design with dynamic relation graph modeling.

PM$_{2.5}$concentration forecasting is important yet challenging. First, complicated local fluctuations in PM$_{2.5}$concentrations disturb modeling global trends. Second, forecasting errors are often accumulated through an autoregressive process. To contend with the two challenges, we propose aCategoryGuidance based PM${_{2.5}}$sequenceForecasting training framework (CGF) to enhance the performance of existing PM${_{2.5}}$concentration forecasting models. CGF contains a Category based Representation Learning (CRL) module and a Category based Self-paced Learning (CSL) module, both of which utilize PM${_{2.5}}$category information that is easily obtained and publicly available. First, CRL employs category information to guide forecasting models to produce more robust hidden representations that are insensitive to local fluctuations, thus alleviating the negative impact of local fluctuations. Second, CSL adaptively selects real PM${_{2.5}}$concentration values versus autoregressive PM${_{2.5}}$forecast values when training forecasting models, helping alleviate error accumulations. The CGF framework is applied to existing PM${_{2.5}}$forecasting models, and the experimental results on two real-world datasets demonstrate that CGF is able to consistently improve the accuracy of existing forecasting models. Furthermore, to validate the generality of CGF, we conduct extensional experiments in two other time-series prediction tasks, including exchange rate forecasting and electricity forecasting. The experimental results also verify the effectiveness of CGF.

Traffic time series forecasting is challenging due to complex spatio-temporal dynamics-time series from different locations often have distinct patterns; and for the same time series, patterns may vary across time, where, for example, there exist certain periods across a day showing stronger temporal correlations. Although recent forecasting models, in particular deep learning based models, show promising results, they suf-fer from being spatio-temporal agnostic. Such spatio-temporal agnostic models employ a shared parameter space irrespective of the time series locations and the time periods and they assume that the temporal patterns are similar across locations and do not evolve across time, which may not always hold, thus leading to sub-optimal results. In this work, we propose a framework that aims at turning spatio-temporal agnostic models to spatio-temporal aware models. To do so, we encode time series from different locations into stochastic variables, from which we generate location-specific and time-varying model parameters to better capture the spatio-temporal dynamics. We show how to integrate the framework with canonical attentions to enable spatio-temporal aware attentions. Next, to compensate for the additional overhead introduced by the spatio-temporal aware model parameter generation process, we propose a novel window attention scheme, which helps reduce the complexity from quadratic to linear, making spatio-temporal aware attentions also have competitive efficiency. We show strong empirical evidence on four traffic time series datasets, where the proposed spatio-temporal aware attentions outperform state-of-the-art methods in term of accuracy and efficiency.

We propose variational quasi-recurrent autoencoders (VQRAEs) to enable robust and efficient anomaly detection in time series in unsupervised settings. The proposed VQRAEs employs a judiciously designed objective function based on robust divergences, including a, ß, and, -divergence, making it possible to separate anomalies from normal data without the reliance on anomaly labels, thus achieving robustness and fully unsupervised training. To better capture temporal dependencies in time series data, VQRAEs are built upon quasi-recurrent neural networks, which employ convolution and gating mechanisms to avoid the inefficient recursive computations used by classic recurrent neural networks. Further, VQRAEs can be extended to bi-directional Bi VQRAEs that utilize bi-directional information to further improve the accuracy. The above design choices make VQRAEs not only robust and thus accurate, but also efficient at detecting anomalies in streaming settings. Experiments on five real-world time series offer insight into the design properties of VQRAEs and demonstrate that VQRAEs are capable of outperforming state-of-the-art methods.

Time series data occurs widely, and outlier detection is a fundamental problem in data mining, which has numerous applications. Existing autoencoder-based approaches deliver state-of-the-art performance on challenging real-world data but are vulnerable to outliers and exhibit low explainability. To address these two limitations, we propose robust and explainable unsupervised auto encoder frameworks that decompose an input time series into a clean time series and an outlier time series using autoencoders. Improved explainability is achieved because clean time series are better explained with easy-to-understand patterns such as trends and periodicities. We provide insight into this by means of a post-hoc explainability analysis and empirical studies. In addition, since outliers are separated from clean time series iteratively, our approach offers improved robustness to outliers, which in turn improves accuracy. We evaluate our approach on five real-world datasets and report improvements over the state-of-the-art approaches in terms of robustness and explainability.

In step with the digitalization of transportation, we are witnessing a growing range of path-based smart-city applications, e.g., travel-time estimation and travel path ranking. A temporal path (TP) that includes temporal information, e.g., departure time, into the path is of fundamental to enable such applications. In this setting, it is essential to learn generic temporal path representations (TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i.e., downstream tasks. Existing methods fail to achieve the goal since (i) supervised methods require large amounts of task-specific labels when training and thus fail to generalize the obtained TPRs to other tasks; (ii) though unsupervised methods can learn generic representations, they disregard the temporal aspect, leading to sub-optimal results. To contend with the limitations of existing solutions, we propose a Weakly-Supervised Contrastive learning model. We first propose a temporal path encoder that encodes both the spatial and temporal information of a temporal path into a TPR. To train the encoder, we introduce weak labels that are easy and inexpensive to obtain, and are relevant to different tasks, e.g., temporal labels indicating peak vs. off-peak hour from departure times. Based on the weak labels, we construct meaningful positive and negative temporal path samples by considering both spatial and temporal information, which facilities training the encoder using contrastive learning by pulling closer the positive samples' representations while pushing away the negative samples' representations. To better guide the contrastive learning, we propose a learning strategy based on Curriculum Learning such that the learning performs from easy to hard training instances. Experimental studies involving three downstream tasks, i.e., travel time estimation, path ranking, and path recommendation, on three road networks offer strong evidence that the proposal is superior to state-of-the-art unsupervised and supervised methods and that it can be used as a pre-training approach to enhance supervised TPR learning.

Retrosynthetic planning, which aims to find a reaction pathway to synthesize a target molecule, plays an important role in chemistry and drug discovery. This task is usually modeled as a search problem. Recently, data-driven methods have attracted many research interests and shown promising results for retrosynthetic planning. We observe that the same intermediate molecules are visited many times in the searching process, and they are usually independently treated in previous tree-based methods (e.g., AND-OR tree search, Monte Carlo tree search). Such redundancies make the search process inefficient. We propose a graph-based search policy that eliminates the redundant explorations of any intermediate molecules. As searching over a graph is more complicated than over a tree, we further adopt a graph neural network to guide the search over graphs. Meanwhile, our method can search a batch of targets together in the graph and remove the inter-target duplication in the tree-based search methods. Experimental results on two datasets demonstrate the effectiveness of our method. Especially on the widely used USPTO benchmark, we improve the search success rate to 99.47%, advancing previous state-of-the-art performance for 2.6 points.

Crowdsourcing aims to enable the assignment of available resources to the completion of tasks at scale. The continued digitization of societal processes translates into increased opportunities for crowdsourcing. For example, crowdsourcing enables the assignment of computational resources of humans, called workers, to tasks that are notoriously hard for computers. In settings faced with malicious actors, detection of such actors holds the potential to increase the robustness of crowdsourcing platform. We propose a framework called Outlier Detection for Streaming Task Assignment that aims to improve robustness by detecting malicious actors. In particular, we model the arrival of workers and the submission of tasks as evolving time series and provide means of detecting malicious actors by means of outlier detection. We propose a novel socially aware Generative Adversarial Network (GAN) based architecture that is capable of contending with the complex distributions found in time series. The architecture includes two GANs that are designed to adversarially train an autoencoder to learn the patterns of distributions in worker and task time series, thus enabling outlier detection based on reconstruction errors. A GAN structure encompasses a game between a generator and a discriminator, where it is desirable that the two can learn to coordinate towards socially optimal outcomes, while avoiding being exploited by selfish opponents. To this end, we propose a novel training approach that incorporates social awareness into the loss functions of the two GANs. Additionally, to improve task assignment efficiency, we propose an efficient greedy algorithm based on degree reduction that transforms task assignment into a bipartite graph matching. Extensive experiments offer insight into the effectiveness and efficiency of the proposed framework.

Ranking paths becomes an increasingly important functionality in many transportation services, where multiple paths connecting a source-destination pair are offered to drivers. We study ranking such paths under specific contexts. More specifically, we model ranking as a regression problem where we assign a ranking score to each path with the help of historical trajectories. To solve the regression problem, we first propose an effective training data enriching method to obtain a compact and diversified set of training paths using historical trajectories. Next, we propose a multi-task learning framework that considers features representing both candidate paths and contexts. Specifically, a road network embedding is proposed to embed paths into feature vectors by considering both road network topology and spatial properties. By modeling different departure times as a temporal graph, graph embedding is used to embed departure times. The objective function not only considers the discrepancies on ranking scores but also the reconstruction errors of the spatial properties of the paths, which in turn improves the final ranking estimation. Empirical studies on a substantial trajectory data set offer insight into the designed properties of the proposed framework and indicating that it is effective and practical in real world settings.

Correlated time series forecasting plays an essential role in many cyber-physical systems, where entities interact with each other over time. To enable accurate forecasting, it is essential to capture both the temporal dynamics and the correlations among different entities. To capture the former, two popular types of models, recurrent neural networks (RNNs) and temporal convolution networks (TCNs), are employed. To capture the latter, a graph is constructed to reflect certain relationships among entities and then graph convolution (GC) is applied upon the graph to capture the correlations among the entities. The state-of-the-art forecasting accuracy is achieved by models that combine RNNs or TCNs with GC. However, they neither capture distinct temporal dynamics that exist among different entities nor consider the entity correlations that evolve across time. In this paper, rather than proposing yet another new end-to-end forecasting model, we aim at providing a framework to enhance existing forecasting models, where we propose generic plugins that can be easily integrated into existing solutions to solve the two challenges and thus further enhance their accuracy. Specifically, we propose two plugin neural networks that are able to better capture distinct temporal dynamics for different entities and dynamic entity correlations across time, so that forecasting accuracy is improved while model parameters to be learned are reduced. Experimental results on three real-world correlated time series data sets demonstrate that the proposed framework with the two plugin networks is able to achieve the above goals.

With the sweeping digitalization of societal, medical, industrial, and scientific processes, sensing technologies are being deployed that produce increasing volumes of time series data, thus fueling a plethora of new or improved applications. In this setting, outlier detection is frequently important, and while solutions based on neural networks exist, they leave room for improvement in terms of both accuracy and efficiency. With the objective of achieving such improvements, we propose a diversity-driven, convolutional ensemble. To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-to-sequence autoencoders that can capture temporal dependencies in time series. Further, a novel diversity-driven training method maintains diversity among the basic models, with the aim of improving the ensemble's accuracy. To improve efficiency, the approach enables a high degree of parallelism during training. In addition, it is able to transfer some model parameters from one basic model to another, which reduces training time. We report on extensive experiments using real-world multivariate time series that offer insight into the design choices underlying the new approach and offer evidence that it is capable of improved accuracy and efficiency.

Correlated time series (CTS) forecasting plays an essential role in many cyber-physical systems, where multiple sensors emit time series that capture interconnected processes. Solutions based on deep learning that deliver state-of-the-art CTS forecasting performance employ a variety of spatio-temporal (ST) blocks that are able to model temporal dependencies and spatial correlations among time series. However, two challenges remain. First, ST-blocks are designed manually, which is time consuming and costly. Second, existing forecasting models simply stack the same ST-blocks multiple times, which limits the model potential. To address these challenges, we propose AutoCTS that is able to automatically identify highly competitive ST-blocks as well as forecasting models with heterogeneous ST-blocks connected using diverse topologies, as opposed to the same ST-blocks connected using simple stacking. Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models. Extensive experiments on eight commonly used CTS forecasting benchmark datasets justify our design choices and demonstrate that AutoCTS is capable of automatically discovering forecasting models that outperform state-of-the-art human-designed models.

Origin-destination (OD) matrices are used widely in transportation and logistics to record the travel cost (e.g., travel speed or greenhouse gas emission) between pairs of OD regions during different intervals within a day. We model a travel cost as a distribution because when traveling between a pair of OD regions, different vehicles may travel at different speeds even during the same interval, e.g., due to different driving styles or different waiting times at intersections. This yields stochastic OD matrices. We consider an increasingly pertinent setting where a set of vehicle trips is used for instantiating OD matrices. Since the trips may not cover all OD pairs for each interval, the resulting OD matrices are likely to be sparse. We then address the problem of forecasting complete, near future OD matrices from sparse, historical OD matrices. To solve this problem, we propose a generic learning framework that (i) employs matrix factorization and graph convolutional neural networks to contend with the data sparseness while capturing spatial correlations and that (ii) captures spatio-temporal dynamics via recurrent neural networks extended with graph convolutions. Empirical studies using two taxi trajectory data sets offer detailed insight into the properties of the framework and indicate that it is effective.

In a cyber-physical system (CPS), different entities often interact with each other across time. With the development of various sensing technologies, the time-varying interactions among entities are often recorded as multiple, correlated time series. A typical CPS is a road transportation system, where the traffic on different road segments interact with each other. Traffic sensors are often deployed to capture travel speeds on different road segments, which results in multiple, potentially correlated, speed time series. Under this setting, an increasingly pertinent task is to forecast future speeds, which is essential in a wide variety of traffic planning scenarios. We present a system for correlated time series forecast. The system is able to employ different learning algorithms to perform correlated time series forecast, which facilities end users to choose the most appropriate algorithm for their specific service. The system is developed and integrated into aSTEP, a spatio-temporal data analytic platform developed by Aalborg University, and is tested using a wide variety of correlated time series data, including a user demand time series from a local mobility-as-a-service company.

Innovations in transportation, such as mobility-on-demand services and autonomous driving, call for high-resolution routing that relies on an accurate representation of travel time throughout the underlying road network. Specifically, the travel time of a road-network edge is modeled as a time-varying distribution that captures the variability of traffic over time and the fact that different drivers may traverse the same edge at the same time at different speeds. Such stochastic weights may be extracted from data sources such as GPS and loop detector data. However, even very large data sources are incapable of covering all edges of a road network at all times. Yet, high-resolution routing needs stochastic weights for all edges. We solve the problem of filling in the missing weights. To achieve that, we provide techniques capable of estimating stochastic edge weights for all edges from traffic data that covers only a fraction of all edges. We propose a generic learning framework called Graph Convolutional Weight Completion (GCWC) that exploits the topology of a road network graph and the correlations of weights among adjacent edges to estimate stochastic weights for all edges. Next, we incorporate contextual information into GCWC to further improve accuracy. Empirical studies using loop detector data from a highway toll gate network and GPS data from a large city offer insight into the design properties of GCWC and its effectiveness.

With the widespread deployment of mobile devices with positioning capabilities, increasingly massive volumes of trajectory data are being collected that capture the movements of people and vehicles. This data enables co-movement pattern detection, which is important in applications such as trajectory compression and future-movement prediction. Existing co-movement pattern detection studies generally consider historical data and thus propose offline algorithms. However, applications such as future movement prediction need real-time processing over streaming trajectories. Thus, we investigate real-time distributed co-movement pattern detection over streaming trajectories. Existing off-line methods assume that all data is available when the processing starts. Nevertheless, in a streaming setting, unbounded data arrives in real time, making pattern detection challenging. To this end, we propose a framework based on Apache Flink, which is designed for efficient distributed streaming data processing. The framework encompasses two phases: clustering and pattern enumeration. To accelerate the clustering, we use a range join based on two-layer indexing, and provide techniques that eliminate unnecessary verifications. To perform pattern enumeration efficiently, we present two methods FBA and VBA that utilize id-based partitioning. When coupled with bit compression and candidate-based enumeration techniques, we reduce the enumeration cost from exponential to linear. Extensive experiments offer insight into the efficiency of the proposed framework and its constituent techniques compared with existing methods.

Cyber-physical systems often consist of entities that interact with each other over time. Meanwhile, as part of the continued digitization of industrial processes, various sensor technologies are deployed that enable us to record time-varying attributes (a.k.a., time series) of such entities, thus producing correlated time series. To enable accurate forecasting on such correlated time series, this paper proposes two models that combine convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The first model employs a CNN on each individual time series, combines the convoluted features, and then applies an RNN on top of the convoluted features in the end to enable forecasting. The second model adds additional auto-encoders into the individual CNNs, making the second model a multi-task learning model, which provides accurate and robust forecasting. Experiments on a large real-world correlated time series data set suggest that the proposed two models are effective and outperform baselines in most settings.

We consider a scenario that occurs often in the auto insurance industry. We are given a large collection of trajectories that stem from many different drivers. Only a small number of the trajectories are labeled with driver identifiers, and only some drivers are used in labels. The problem is to label correctly the unlabeled trajectories with driver identifiers. This is important in auto insurance to detect possible fraud and to identify the driver in, e.g., pay-as-you-drive settings when a vehicle has been involved in an incident. To solve the problem, we first propose a Trajectory-to-Image( T2I) encoding scheme that captures both geographic features and driving behavior features of trajectories in 3D images. Next, we propose a multi-task, deep learning model called T2INet for estimating the total number of drivers in the unlabeled trajectories, and then we partition the unlabeled trajectories into groups so that the trajectories in a group belong to the same driver. Experimental results on a large trajectory data set offer insight into the design properties of T2INet and demonstrate that T2INet is capable of outperforming baselines and the state-of-the-art method.

Motivated by the increasing availability of vehicle trajectory data, we propose learn-to-route, a comprehensive trajectory-based routing solution. Specifically, we first construct a graph-like structure from trajectories as the routing infrastructure. Second, we enable trajectory-based routing given an arbitrary (source, destination) pair. In the first step, given a road network and a collection of trajectories, we propose a trajectory-based clustering method that identifies regions in a road network. If a pair of regions are connected by trajectories, we maintain the paths used by these trajectories and learn a routing preference for travel between the regions. As trajectories are skewed and sparse, %and although the introduction of regions serves to consolidate the sparse data, many region pairs are not connected by trajectories. We thus transfer routing preferences from region pairs with sufficient trajectories to such region pairs and then use the transferred preferences to identify paths between the regions. In the second step, we exploit the above graph-like structure to achieve a comprehensive trajectory-based routing solution. Empirical studies with two substantial trajectory data sets offer insight into the proposed solution, indicating that it is practical. A comparison with a leading routing service offers evidence that the paper's proposal is able to enhance routing quality.

Indoor tracking data is being amassed due to the deployment of indoor positioning technologies. Analysing such data discloses useful insights that are otherwise hard to obtain. For example, by studying tracking data from an airport, we can identify the shops and restaurants that are most popular among passengers. In this paper, we study two query types for finding frequently visited Points of Interest (POIs) from symbolic indoor tracking data. The snapshot query finds those POIs that were most frequently visited at a given time point, whereas the interval query finds such POIs for a given time interval. A typical example of symbolic tracking is RFID-based tracking, where an object with an RFID tag is detected by an RFID reader when the object is in the reader’s detection range. A symbolic indoor tracking system deploys a limited number of proximity detection devices, like RFID readers, at preselected locations, covering only part of the host indoor space. Consequently, symbolic tracking data is inherently uncertain and only enables the discrete capture of the trajectories of indoor moving objects in terms of coarse regions. We provide uncertainty analyses of the data in relation to the two kinds of queries. The outcomes of the analyses enable us to design processing algorithms for both query types. An experimental evaluation with both real and synthetic data suggests that the framework and algorithms enable efficient and scalable query processing.

With the growing volumes of vehicle trajectory data, it becomes increasingly possible to capture time-varying and uncertain travel costs in a road network, including travel time and fuel consumption. The current paradigm represents a road network as a weighted graph; it blasts trajectories into small fragments that fit the under-lying edges to assign weights to edges; and it then applies a routing algorithm to the resulting graph. We propose a new paradigm, the hybrid graph , that targets more accurate and more efficient path cost distribution estimation. The new paradigm avoids blasting trajectories into small fragments and instead assigns weights to paths rather than simply to the edges. We show how to compute path weights using trajectory data while taking into account the travel cost dependencies among the edges in the paths. Given a departure time and a query path, we show how to select an optimal set of weights with associated paths that cover the query path and such that the weights enable the most accurate joint cost distribution estimation for the query path. The cost distribution of the query path is then computed accurately using the joint distribution. Finally, we show how the resulting method for computing cost distributions of paths can be integrated into existing routing algorithms. Empirical studies with substantial trajectory data from two different cities offer insight into the design properties of the proposed method and confirm that the method is effective in real-world settings.

When planning routes, drivers usually consider a multitude of different travel costs, e.g., distances, travel times, and fuel consumption. Different drivers may choose different routes between the same source and destination because they may have different driving preferences (e.g., time-efficient driving v.s. fuel-efficient driving). However, existing routing services support little in modeling multiple travel costs and personalization-they usually deliver the same routes that minimize a single travel cost (e.g., the shortest routes or the fastest routes) to all drivers. We study the problem of how to recommend personalized routes to individual drivers using big trajectory data. First, we provide techniques capable of modeling and updating different drivers' driving preferences from the drivers' trajectories while considering multiple travel costs. To recommend personalized routes, we provide techniques that enable efficient selection of a subset of trajectories from all trajectories according to a driver's preference and the source, destination, and departure time specified by the driver. Next, we provide techniques that enable the construction of a small graph with appropriate edge weights reflecting how the driver would like to use the edges based on the selected trajectories. Finally, we recommend the shortest route in the small graph as the personalized route to the driver. Empirical studies with a large, real trajectory data set from 52,211 taxis in Beijing offer insight into the design properties of the proposed techniques and suggest that they are efficient and effective.

Reduction in greenhouse gas emissions from transportation attracts increasing interest from governments, fleet managers, and individual drivers. Eco-routing, which enables drivers to use eco-friendly routes, is a simple and effective approach to reducing emissions from transportation. We present EcoSky, a system that annotates edges of a road network with time dependent and uncertain eco-weights using GPS data and that supports different types of eco-routing. Basic eco-routing returns the most eco-friendly routes; skyline eco-routing takes into account not only fuel consumption but also travel time and distance when computing eco-routes; and personalized eco-routing considers each driver's past behavior and accordingly suggests different routes to different drivers.

Different uses of a road network call for the consideration of different travel costs: in route planning, travel time and distance are typically considered, and green house gas (GHG) emissions are increasingly being considered. Further, travel costs such as travel time and GHG emissions are time-dependent and uncertain. To support such uses, we propose techniques that enable the construction of a multi-cost, time-dependent, uncertain graph (MTUG) model of a road network based on GPS data from vehicles that traversed the road network. Based on the MTUG, we define stochastic skyline routes that consider multiple costs and time-dependent uncertainty, and we propose efficient algorithms to retrieve stochastic skyline routes for a given source-destination pair and a start time. Empirical studies with three road networks in Denmark and a substantial GPS data set offer insight into the design properties of the MTUG and the efficiency of the stochastic skyline routing algorithms.

The monitoring of a system can yield a set of measurements that can be modeled as a collection of time series. These time series are often sparse, due to missing measurements, and spatiotemporally correlated, meaning that spatially close time series exhibit temporal correlation. The analysis of such time series offers insight into the underlying system and enables prediction of system behavior. While the techniques presented in the paper apply more generally, we consider the case of transportation systems and aim to predict travel cost from GPS tracking data from probe vehicles. Specifically, each road segment has an associated travel-cost time series, which is derived from GPS data. We use spatio-temporal hidden Markov models (STHMM) to model correlations among different traffic time series. We provide algorithms that are able to learn the parameters of an STHMM while contending with the sparsity, spatio-temporal correlation, and heterogeneity of the time series. Using the resulting STHMM, near future travel costs in the transportation network, e.g., travel time or greenhouse gas emissions, can be inferred, enabling a variety of routing services, e.g., eco-routing. Empirical studies with a substantial GPS data set offer insight into the design properties of the proposed framework and algorithms, demonstrating the effectiveness and efficiency of travel cost inferencing.

The reduction of greenhouse gas (GHG) emissions from transportation is essential for achieving politically agreed upon emissions reduction targets that aim to combat global climate change. So-called eco-routing and eco-driving are able to substantially reduce GHG emissions caused by vehicular transportation. To enable these, it is necessary to be able to reliably quantify the emissions of vehicles as they travel in a spatial network. Thus, a number of models have been proposed that aim to quantify the emissions of a vehicle based on GPS data from the vehicle and a 3D model of the spatial network the vehicle travels in. We develop an evaluation framework, called EcoMark, for such environmental impact models. In addition, we survey all eleven state-of-the-art impact models known to us. To gain insight into the capabilities of the models and to understand the effectiveness of the EcoMark, we apply the framework to all models.

The vision of dataspaces proposes an alternative to classical data integration approaches with reduced up-front costs followed by incremental improvement on a pay-as-you-go basis. In this paper, we demonstrate DSToolkit, a system that allows users to provide feedback on results of queries posed over an integration schema. Such feedback is then used to annotate the mappings with their respective precision and recall. The system then allows a user to state the expected levels of precision (or recall) that the query results should exhibit and, in order to produce those results, the system selects those mappings that are predicted to meet the stated constraints.