Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what extent can we localise spatial-temporal graph models? We limit our scope to adaptive spatial-temporal graph neural networks (ASTGNNs), the state-of-the-art model architecture. Our approach to localisation involves sparsifying the spatial graph adjacency matrices. To this end, we propose Adaptive Graph Sparsification (AGS), a graph sparsification algorithm which successfully enables the localisation of ASTGNNs to an extreme extent (fully localisation). We apply AGS to two distinct ASTGNN architectures and nine spatial-temporal datasets. Intriguingly, we observe that spatial graphs in ASTGNNs can be sparsified by over 99.5\% without any decline in test accuracy. Furthermore, even when ASTGNNs are fully localised, becoming graph-less and purely temporal, we record no drop in accuracy for the majority of tested datasets, with only minor accuracy deterioration observed in the remaining datasets. However, when the partially or fully localised ASTGNNs are reinitialised and retrained on the same data, there is a considerable and consistent drop in accuracy. Based on these observations, we reckon that \textit{(i)} in the tested data, the information provided by the spatial dependencies is primarily included in the information provided by the temporal dependencies and, thus, can be essentially ignored for inference; and \textit{(ii)} although the spatial dependencies provide redundant information, it is vital for the effective training of ASTGNNs and thus cannot be ignored during training. Furthermore, the localisation of ASTGNNs holds the potential to reduce the heavy computation overhead required on large-scale spatial-temporal data and further enable the distributed deployment of ASTGNNs.
ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
School of Data Science and Engineering, East China Normal University, Shanghai, China（东华大学数据科学与工程学院，上海，中国）；Engineering Research Center of Blockchain Data Management, Ministry of Education, China（教育部区块链数据管理工程研究中心，中国）
DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting
Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai（能源化学过程智能制造关键实验室，教育部，东华大学，上海）；Faculty of Informatics, Università della Svizzera italiana（瑞士意大利大学信息学院）；Department of Electronics, Information and Bioengineering, Politecnico di Milano（米兰理工学院电子、信息与生物工程系）
Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
Faculty of Electronic and Information Engineering, Xi’an Jiaotong University（电子与信息工程学院，西安交通大学）；Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人工智能与机器人研究院，西安交通大学）；State Key Lab of Brain-Machine Intelligence, Zhejiang University（脑机智能国家重点实验室，浙江大学）；School of Computer Science, Dalian University of Technology（计算机科学学院，大连理工大学）；National Key Lab of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University（人机混合增强智能国家实验室，西安交通大学）
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD)（eBRAIN实验室，工程学院，纽约大学阿布扎比分校）；Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD（量子与拓扑系统中心（CQTS），NYUAD研究院，NYUAD）；Indian Institute of Technology Palakkad (IITPKD)（帕拉卡德印度理工学院（IITPKD））
Adaptive Pseudo-Siamese Policy Network for Temporal Knowledge Prediction
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Double-Path Adaptive-correlation Spatial-Temporal Inverted Transformer for Stock Time Series Forecasting
School of Intelligence Science and Technology（智能科学与技术学院）；Computational Intelligence Laboratory（计算智能实验室）；National Key Laboratory of General Artificial Intelligence（通用人工智能全国重点实验室）；Key Laboratory of Machine Perceptron (MOE)（教育部机器感知重点实验室）
AdaRNN: Adaptive Learning and Forecasting of Time Series
Nanjing University（南京大学）；Microsoft Research Asia（微软亚洲研究院）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Zhejiang University（浙江大学）
Fine-grained Spatio-temporal Event Prediction with Self-adaptive Anchor Graph
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳高等研究院）；Kashi Institute of Electronics and Information Industry（喀什电子信息产业研究院）
Multi-modal Adaptive Estimation for Temporal Respiratory Disease Outbreak
Respiratory Disease AI Laboratory in Epidemic Intelligence and Applications of Medical Big Data Instruments, Macau University of Science and Technology（呼吸疾病人工智能实验室（流行病智能与医学大数据应用））；Faculty of Innovation Engineering, Macau University of Science and Technology（创新工程学院）；Institute of Systems Engineering, Macau University of Science and Technology（系统工程研究所）；School of Business, Macau University of Science and Technology（商学院）；State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University（呼吸疾病国家重点实验室、呼吸疾病临床研究中心、广州呼吸健康研究院、广州医学院第一附属医院）；Guangzhou National Laboratory（广州国家实验室）
