Time series forecasting and spatiotemporal kriging are the two most important tasks in spatiotemporal data analysis. Recent research on graph neural networks has made substantial progress in time series forecasting, while little attention has been paid to the kriging problem -- recovering signals for unsampled locations/sensors. Most existing scalable kriging methods (e.g., matrix/tensor completion) are transductive, and thus full retraining is required when we have a new sensor to interpolate. In this paper, we develop an Inductive Graph Neural Network Kriging (IGNNK) model to recover data for unsampled sensors on a network/graph structure. To generalize the effect of distance and reachability, we generate random subgraphs as samples and reconstruct the corresponding adjacency matrix for each sample. By reconstructing all signals on each sample subgraph, IGNNK can effectively learn the spatial message passing mechanism. Empirical results on several real-world spatiotemporal datasets demonstrate the effectiveness of our model. In addition, we also find that the learned model can be successfully transferred to the same type of kriging tasks on an unseen dataset. Our results show that: 1) GNN is an efficient and effective tool for spatial kriging; 2) inductive GNNs can be trained using dynamic adjacency matrices; 3) a trained model can be transferred to new graph structures and 4) IGNNK can be used to generate virtual sensors.
Spatiotemporal kriging is an important application in spatiotemporal data analysis, aiming to recover/interpolate signals for unsampled/unobserved locations based on observed signals. The principle challenge for spatiotemporal kriging is how to effectively model and leverage the spatiotemporal dependencies within the data. Recently, graph neural networks (GNNs) have shown great promise for spatiotemporal kriging tasks. However, standard GNNs often require a carefully designed adjacency matrix and specific aggregation functions, which are inflexible for general applications/problems. To address…
Xiamen University（厦门大学）；University of Melbourne（墨尔本大学）；Zhejiang University（浙江大学）
Spatio-temporal kriging is an important problem in web and social applications, such as Web or Internet of Things, where things (e.g., sensors) connected into a web often come with spatial and temporal properties. It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest. This problem essentially requires \emph{inductive learning}. Once trained, the model should be able to perform kriging for different locations including newly given ones, without retraining. However, it is challenging to pe…
KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy
S-Lab, Nanyang Technological University（新加坡南洋理工大学S-Lab）；University of Cologne（科隆大学）；Beijing Institute of Technology（北京理工大学）；SenseTime Research（商汤科技研究院）
AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging
School of Computer Science（计算机科学学院）；University of Auckland（奥克兰大学）；Shenzhen Key Laboratory of Internet Information Collaboration（互联网信息协作深圳实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳学院）
Gaussian random fields (GRF) are a fundamental stochastic model for spatiotemporal data analysis. An essential ingredient of GRF is the covariance function that characterizes the joint Gaussian distribution of the field. Commonly used covariance functions give rise to fully dense and unstructured covariance matrices, for which required calculations are notoriously expensive to carry out for large data. In this work, we propose a construction of covariance functions that result in matrices with a hierarchical structure. Empowered by matrix algorithms that scale linearly with the matrix dimensio…
Periodic monitoring of groundwater quality at industrial and commercial sites generates large volumes of spatiotemporal concentration data. Data modelling is typically restricted to either the analysis of monotonic trends in individual wells, or independent fitting of spatial concentration distributions (e.g. Kriging) to separate monitoring time periods. Neither of these techniques satisfactorily elucidate the interaction between spatial and temporal components of the data. Potential negative consequences include an incomplete understanding of groundwater plume dynamics, which can lead to the …
Physics-Guided Inductive Spatiotemporal Kriging for PM2.5 with Satellite Gradient Constraints
School of Systems Science, Beijing Normal University（北京师范大学系统科学学院）；College of Information Engineering, Jiangxi University of Science and Technology（江西理工大学信息工程学院）；D-ITET, ETH Zurich（ETH Zurich的D-ITET）；Graz University of Technology（格拉茨技术大学）；ColorfulClouds Technology Co.,Ltd.（ColorfulClouds技术有限公司）；State Key Laboratory of Earth Surface Processes and Disaster Risk Reduction, Beijing Normal University（北京师范大学地球表层过程与灾害风险降低国家重点实验室）
ST-GRIT: Spatio-Temporal Graph Transformer For Internal Ice Layer Thickness Prediction
Department of Computer Science and Engineering, Lehigh University, PA, USA（计算机科学与工程系，莱霍夫大学）；Department of Civil and Environmental Engineering, Lehigh University, PA, USA（土木与环境工程系，莱霍夫大学）
GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction
Department of Computer Science and Engineering, Lehigh University（计算机科学与工程系，莱恩大学）；Department of Civil and Environmental Engineering, Lehigh University（土木与环境工程系，莱恩大学）
PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
School of Data Science（数据科学学院）；University of Virginia（弗吉尼亚大学）；Department of Astronomy（天文学系）；Department of Mechanical Engineering（机械工程系）；University of Iowa（爱荷华大学）；School of Mechanical Engineering（机械工程学院）；Kyungpook National University（庆北国立大学）；Department of Mechanical and Aerospace Engineering（机械与航空航天工程系）
The Chinese University of Hong Kong（香港中文大学）；Hong Kong University of Science and Technology（香港科技大学）；Amazon Web Services（亚马逊网络服务）；Microsoft Research（微软研究院）
We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head's importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves stat…
Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
German Research Center for Artificial Intelligence (DFKI), Data Science and its Applications Research Group, Kaiserslautern, Germany（德国人工智能研究中心（DFKI），数据科学及其应用研究组，凯泽斯劳滕，德国）；Department of Computer Science, Rhineland-Palatinate Technical University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany（计算机科学系，莱茵兰-普法尔茨凯泽斯劳滕-兰道工业大学（RPTU），凯泽斯劳滕，德国）
Renault Automotive（雷诺汽车公司）；Axionable Labs（Axionable实验室）
We propose a methodology to extend the concept of Two-Stream Convolutional Networks to perform end-to-end learning for self-driving cars with temporal cues. The system has the ability to learn spatiotemporal features by simultaneously mapping raw images and pre-calculated optical flows directly to steering commands. Although optical flows encode temporal-rich information, we found that 2D-CNNs are prone to capturing features only as spatial representations. We show how the use of Multitask Learning favors the learning of temporal features via inductive transfer from a shared spatiotemporal rep…
Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows
State Key Laboratory for Turbulence and Complex Systems, School of Mechanics and Engineering Science, Peking University（湍流与复杂系统国家重点实验室，力学与工程科学学院，北京大学）；Gaoling School of Artificial Intelligence, Renmin University of China（Gallagher人工智能学院，中国人民大学）；AI for Science Institute（人工智能科学研究院）；University of Calgary（卡尔加里大学）；Kyoto University（京都大学）；FM Global（FM全球）；LandSpace Technology Corporation Ltd.（陆地方向技术有限公司）；Aero Engine Academy of China（中国航空发动机学院）
Stable spectral neural operator for learning stiff PDE systems from limited data
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院（ Gallagher 学院））；School of Engineering Science, University of Chinese Academy of Sciences（中国科学院大学工程科学学院）
Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting
SUSTech-UTokyo Joint Research Center on Super Smart City（南方科技大学-东京大学超级智慧城市联合研究中心）；Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology (SUSTech)（南方科技大学可信自主系统研究院）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Center for Spatial Information Science, University of Tokyo（东京大学空间信息科学中心）
Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data
School of Transportation, Jilin University（吉林大学交通运输学院）；Department of Computer Science, City University of Hong Kong (Dongguan)（香港城市大学（东莞）计算机科学系）；Institute for Transport Planning and Systems, ETH Zurich（苏黎世联邦理工学院交通规划与系统研究所）；Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University（浙江大学智能交通系统研究所）；ZJU-UIUC Institute, Zhejiang University（浙江大学-UIUC研究院）
PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problems
Department of Computer Science, UC Berkeley（计算机科学系，加州大学伯克利分校）；UC Berkeley（加州大学伯克利分校）；Departments of Computer Science and Chemical Engineering UC Berkeley（计算机科学与化学工程系，加州大学伯克利分校；劳伦斯伯克利国家实验室）；LBNL
