Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting
ICube, University of Strasbourg, Illkirch-Graffenstaden, France(斯特拉斯堡大学ICube研究所,法国伊尔克里奇-格拉夫芬斯坦德);Technical University of Munich(慕尼黑技术大学);FinTech Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)金融科技研究组);Computer Science Department, Hainan Bielefeld University of Applied Sciences(海南比尔费尔德应用科学大学计算机科学系);Cephalgo, Strasbourg, France(法国斯特拉斯堡Cephalgo公司);Heilbronn Data Science Center, Munich Data Science Institute(慕尼黑数据科学研究所海德堡数据科学中心)
Federico Zucchi, Yi Xie, Chao Zhang, Thomas Lampert, Ziyue Li
Adaptive patching has been proposed for time-series forecasting: allocate finer patches where the sequence looks locally informative. We compare three adaptive patching methods with tuned uniform counterparts that use one fixed patch size throughout the input, while preserving each method's backbone family and shared training protocol. Across the evaluated long-horizon benchmarks, we observe mostly small accuracy differences and no consistent advantage for adaptive patching; uniform variants generally train faster and avoid adaptive routing at inference. Motivated by these observations, we develop a theoretical framework for budgeted patch allocation through a common resolution-density representation of uniform, nonuniform, and overlapping layouts, independently of the patching rule. Within a separable shared-loss model, we derive an exact criterion for when nonuniform allocation improves on uniform allocation at the same budget. We characterize modeled gains locally through a quadratic surrogate and bound them globally under strong convexity and a bounded loss derivative. The analysis distinguishes where resolution is placed from how much it is redistributed: even an allocation that correctly ranks regions by their weights can redistribute too much resolution and increase modeled loss. Without coupling across time, positive regional weights preserve the minimizers of the shared loss. When the shared loss has a common minimizing rate, the remaining absolute headroom for improvement tends to zero as the uniform rate approaches it. These results characterize the roles of regional weighting, placement, and redistribution strength under the stated model. The empirical findings support evaluating adaptive patching against a tuned uniform baseline and weighing any accuracy gain against the additional training and inference cost of adaptive routing.
TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss
College of Electrical Engineering, Sichuan University(四川大学电气工程学院);College of Architecture and Environment, Sichuan University(四川大学建筑与环境学院);State Grid Sichuan Electric Power Research Institute(国网四川省电力公司电力科学研究院);College of Computer Science, Sichuan University(四川大学计算机学院)
Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting
School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院);Innovation Engineering College, Macau University of Science and Technology(澳门科技大学创新工程学院)
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))
DA-SPS: A Dual-stage Network based on Singular Spectrum Analysis, Patching-strategy and Spearman-correlation for Multivariate Time-series Prediction
Department of Automation, University of Science and Technology of China(自动化系,中国科学技术大学);Institute of Advanced Technology, University of Science and Technology of China(先进技术研究院,中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥综合性国家科学中心)
Unlocking the Power of LSTM for Long Term Time Series Forecasting
University of Oxford(牛津大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Princeton University(普林斯顿大学);Alibaba Group(阿里巴巴集团);Duke Kunshan University(昆山杜克大学);Squirrel AI(松鼠AI)
TSGym: Design Choices for Deep Multivariate Time-Series Forecasting
AI Lab, Shanghai University of Finance and Economics(上海财经大学金融学院人工智能实验室);Ant Group(蚂蚁集团);MoE Key Laboratory of Interdisciplinary Research of Computation and Economics(计算与经济学交叉学科关键实验室)
Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting
School of Computing, Macquarie University(麦考瑞大学计算机学院);Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系);department of Electrical and Electronic Engineering, Hong Kong Polytechnic University(香港理工大学电子与电气工程系)
CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationarity
organization= Department of Computer Engineering , addressline= Middle East Technical University , city= Ankara , postcode= 06800 , country= Turkey;organization= METU-BILTIR CAD/CAM \& Robotics Research Center , addressline= Middle East Technical University , city= Ankara , postcode= 06800 , country= Turkey
SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models
School of Artificial Intelligence, Nanjing University, China(人工智能学院,南京大学);National Key Laboratory for Novel Software Technology, Nanjing University, China(新型软件技术国家重点实验室,南京大学);School of Electronic Science and Engineering, Nanjing University, China(电子科学与工程学院,南京大学)
本文提出 SPAT 结构化剪枝方法,利用动态 SEND 指标识别并移除整个冗余注意力模块,在多元时间序列预测中降低误差与 FLOPs,并超越多种 SOTA 方法。
Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(南洋理工大学电子与电气工程学院);Institute for Infocomm Research, A*STAR, Singapore(信息通信研究所,A*STAR,新加坡);Department of Computer Science, Khalifa University, UAE(计算机科学系,哈利法大学,阿联酋);Information Systems Technology and Design, Singapore University of Technology and Design, Singapore(信息系统技术与设计,新加坡科技与设计大学,新加坡)
FRWKV+: Periodic-Aware Adaptive Gating for Frequency-Space Linear Time Series Forecasting
College of Information Science and Engineering, Northeastern University(信息科学与工程学院,东北大学);Foshan Graduate School of Innovation, Northeastern University(创新研究生学院,东北大学);National Frontiers Science Center for Industrial Intelligence and Systems Optimization(工业智能与系统优化国家级前沿科学中心)
Probabilistic Forecasting of Radiation Exposure for Spaceflight
UC Riverside(加州大学河滨分校);UC Berkeley(加州大学伯克利分校);University of Washington(华盛顿大学);University of Cambridge(剑桥大学);University College London(伦敦大学学院);University of New Hampshire(新罕布什尔大学);University of Oxford(牛津大学)
PLanTS: Periodicity-aware Latent-state Representation Learning for Multivariate Time Series
Department of Computer Science(计算机科学系);Indiana University(印第安纳大学);Department of Biomedical Engineering(生物医学工程系);Oregon Health & Science University(俄勒冈健康与科学大学)