Foundation Models for Time Series Analysis: A Tutorial and Survey
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Beijing Jiao Tong University(北京交通大学);HKUST(GZ)(香港科技大学(广州));Princeton University(普林斯顿大学);University of Connecticut(康涅狄格大学);Monash University(莫纳什大学);Griffith University(格里菲斯大学);Squirrel AI(松鼠AI)
Yuxuan Liang, Haomin Wen, Yuqi Nie, Yushan Jiang, Ming Jin, Dongjin Song, Shirui Pan, Qingsong Wen
Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications. Recent advances in Foundation Models (FMs) have fundamentally reshaped the paradigm of model design for time series analysis, boosting various downstream tasks in practice. These innovative approaches often leverage pre-trained or fine-tuned FMs to harness generalized knowledge tailored for time series analysis. This survey aims to furnish a comprehensive and up-to-date overview of FMs for time series analysis. While prior surveys have predominantly focused on either application or pipeline aspects of FMs in time series analysis, they have often lacked an in-depth understanding of the underlying mechanisms that elucidate why and how FMs benefit time series analysis. To address this gap, our survey adopts a methodology-centric classification, delineating various pivotal elements of time-series FMs, including model architectures, pre-training techniques, adaptation methods, and data modalities. Overall, this survey serves to consolidate the latest advancements in FMs pertinent to time series analysis, accentuating their theoretical underpinnings, recent strides in development, and avenues for future exploration.
A Tutorial on Distance Metric Learning: Mathematical Foundations, Algorithms, Experimental Analysis, Prospects and Challenges (with Appendices on Mathematical Background and Detailed Algorithms Explanation)
DaSCI, Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI 安达卢西亚数据科学与计算智能研究所);University of Granada(格拉纳达大学)
Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Carnegie Mellon University(卡内基梅隆大学);National University of Singapore(新加坡国立大学);Griffith University(格里菲斯大学);East China Normal University(华东师范大学);University of New South Wales(新南威尔士大学);Squirrel Ai Learning, USA(美国松鼠人工智能学习公司);Nanyang Technology University(南洋理工大学)
A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
University of Minnesota(明尼苏达大学);Univ. Guatave Eiffel, ENTPE, LICIT-ECO7(埃弗尔大学);Urban Transport Systems Laboratory (LUTS), École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院交通系统实验室);National University of Singapore(新加坡国立大学);The University of Queensland(昆士兰大学);McGill University(麦吉尔大学)
How Foundational are Foundation Models for Time Series Forecasting?
Univ. Rennes(里昂大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化技术研究所);IRISA - UMR 6074(国际信息与自动化研究所);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Univ. Savoie Mont Blanc(萨瓦伊-蒙布莱大学);LPNC(实验室);CEA(法国原子能委员会);LIST(法国国家信息与自动化技术研究所)
TimeFound: A Foundation Model for Time Series Forecasting
Baidu Research(百度研究院);University of Science and Technology of China(中国科学技术大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
University of Technology Nuremberg(纽伦堡工业大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Alberta(阿尔伯塔大学);ETH Zürich(苏黎世联邦理工学院);University of California San Diego(加州大学圣迭戈分校)
Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
AGH University of Krakow, Poland(克拉科夫AGH大学);Institut de Neurosciences de la Timone UMR 7289, Aix Marseille Université, CNRS, 13005, Marseille, France(里莫内神经科学研究所)
LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions
Nanyang Technological University(南洋理工大学);The Hong Kong Polytechnic University(香港理工大学);University of Electronic Science and Technology of China(电子科学与技术大学);Technical University of Munich(慕尼黑技术大学);King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹大学)
Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models
Salesforce AI Research(Salesforce AI研究院);National University of Singapore(新加坡国立大学);Squirrel Ai Learning(松鼠人工智能学习);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Synthetic Series-Symbol Data Generation for Time Series Foundation Models
School of Telecommunications Engineering Xidian University(电子科技大学电信工程学院);School of Artificial Intelligence Xidian University(电子科技大学人工智能学院);School of Cyber Engineering Xidian University(电子科技大学网络安全工程学院)
Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
School of Artificial Intelligence, Xidian University(西安电子科技大学人工智能学院);The State Key Laboratory of Integrated Services Networks(综合业务网络国家重点实验室);School of Network and Information Security, Xidian University(西安电子科技大学网络与信息安全学院)
Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning
School of Software Engineering(软件工程学院);National Key Laboratory of Fundamental Science of Synthetic Vision(合成视觉基础科学国家重点实验室);School of Mechanical Engineering(机械工程学院);China Electric Power Research Institute(中国电力科学研究院);School of Computer Science(计算机科学学院)