Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces. In this work, we consider a setting in which time series live on different spaces without a sensible ground metric, causing DTW to become ill-defined. To alleviate this, we propose Gromov dynamic time warping (GDTW), a distance between time series on potentially incomparable spaces that avoids the comparability requirement by instead considering intra-relational geometry. We demonstrate its effectiveness at aligning, combining and comparing time series living on incomparable spaces. We further propose a smoothed version of GDTW as a differentiable loss and assess its properties in a variety of settings, including barycentric averaging, generative modeling and imitation learning.
Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis
State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)
LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
Institute for Clarity in Documentation(文献清晰研究所);The Thørväld Group(索沃尔德集团);Inria(法国国家信息与自动化研究所);Rajiv Gandhi University(拉吉夫·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕尔默研究实验室);The Kumquat Consortium(柑橘联盟)
A Supervised Contrastive Learning Pretrain-Finetune Approach for Time Series
School of Operations Research and Information Engineering, Cornell University(康奈尔大学运筹学与信息工程学院);IBM Research, Thomas J. Watson Research Center(IBM研究部托马斯·J·沃森研究中心)
LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
Hong Kong University of Science and Technology(香港科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));University of Cologne(科隆大学)
TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning
Agentic Systems Lab, ETH Zurich(1 非常规系统实验室,苏黎世联邦理工学院);Stanford University(2 斯坦福大学);Traffic Engineering Group, Institute for Transport Planning and Systems, ETH Zurich(3 交通工程组,交通规划与系统研究所,苏黎世联邦理工学院);University of Illinois Urbana-Champaign(4 印第安纳大学厄巴纳-香槟分校);Google(5 谷歌);Centre for Digital Health Interventions, ETH Zurich(6 数字健康干预中心,苏黎世联邦理工学院);Centre for Digital Health Interventions, University of St. Gallen(7 数字健康干预中心,圣加尔登大学)
A diffusion-based generative model for financial time series via geometric Brownian motion
Department of Mathematics, POSTECH(POSTECH数学系);Department of Financial Mathematics, Gachon University(高丽大学金融数学系);Department of Applied Artificial Intelligence, SeoulTech(首尔科技大学应用人工智能系)
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究所);ByteDance(字节跳动);National Institute of Health Data Science, Peking University(北京大学国家健康数据科学研究院)
Cropland PAtteRNS: Parallel Dimensional Attention Networks and Attention to Dataset Disparity for Crop Segmentation in Satellite Imagery Time Series Data
LLM-ABBA: Understanding time series via symbolic approximation
Sorbonne Université, CNRS, LIP6(索邦大学、法国国家科学研究中心、LIP6实验室);Department of Numerical Mathematics, Charles University(数值数学系、查尔斯大学);Department of Cybernetics, Czech Technical University in Prague(控制论系、布拉格捷克技术大学)
Xiaohongshu Inc.(小红书公司);College of Control Science and Technology, Zhejiang University(浙江大学控制科学与工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics(上海财经大学计算与人工智能学院);State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室);Squirrel AI(松鼠AI);Center for Data Science, Peking University(北京大学数据科学中心);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
Deep Time-series Forecasting Needs Kernelized Moment Balancing
Xiaohongshu Inc.(小红书公司);National University of Singapore(新加坡国立大学);The City University of New York, CUNY(纽约市立大学,CUNY);State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(人工智能国家重点实验室,北京大学);Center for Data Science, Peking University(北京大学数据科学中心);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Monash University(莫纳什大学);Ant Group(蚂蚁集团);IBM Research(IBM研究院);Griffith University(格里菲斯大学);Alibaba Group(阿里巴巴集团);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification
Xi’an Institute of Optics and Precision Mechanics, CAS(西安光学精密机械研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Southwest Jiaotong University(西南交通大学);Zhongnan Hospital of Wuhan University(武汉大学中南医院);Xi’an Jiaotong University(西安交通大学);National Key Laboratory of Information Systems Engineering(信息系统工程国家重点实验室)
本文提出通道强制融合(CIF)方法,通过跨通道信息融合增强信噪比并减少冗余,结合时间卷积网络(TCN)构建结构透明、高效的医学时间序列分类框架,在多个 EEG 和 ECG 数据集上超越现有 SOTA 方法并提升分类过程透明性。
Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data
College of Computing and Data Science, Nanyang Technological University (NTU), Singapore(南洋理工大学计算与数据科学学院);School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics(江西财经大学计算机与人工智能学院);Institute for Infocomm Research (I 2 R), A*STAR, Singapore(信息通信研究所(I2R),A*STAR,新加坡);School of Artificial Intelligence, Nanjing University of Information Science and Technology(南京信息科学技术大学人工智能学院)
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(新加坡南洋理工大学电气与电子工程学院);School of Computer Science and Engineering, Nanyang Technological University, Singapore(新加坡南洋理工大学计算机科学与工程学院)