Long-term time series forecasting requires learning temporal dependencies that remain stable and generalizable under temporal distribution shifts. However, real-world time series are often noisy, non-stationary, and heterogeneous, making deep learning models prone to overfitting incidental temporal interactions in the training data. This raises a question: when observations are difficult to align, could temporal relationships be easier to reuse? To investigate this possibility, we analyze patch-level temporal relationship matrices across commonly used time series datasets, revealing dominant patterns shared across different temporal windows and variables. Comparisons with patch-shuffled and IID Gaussian controls further support the presence of reusable temporal relationship structures. Motivated by these findings, we propose \textbf{T}emporal \textbf{Struct}ure Network (\textbf{TStruct}), a simple yet effective network that learns reusable temporal dependency structures and adaptively combines them for each sample and variable. Specifically, TStruct directly parameterizes a set of shared temporal dependency matrices and generates normalized combination weights using dynamic sample information and static variable priors. These weights represent a soft allocation of each sample-variable pair over shared temporal dependency structures, enabling the model to generate adaptive temporal dependency matrices under shared structural constraints, rather than fitting incidental interactions in a fully unconstrained manner. Notably, TStruct consistently outperforms several strong baselines across all evaluated datasets, achieving superior accuracy while maintaining high computational efficiency. Our code is available at https://github.com/yangzeli/TStruct.
Self-Gating Attention for Efficient Time Series Forecasting
School of Automation, Southeast University(自动化学院,东南大学);School of Electrical Engineering and Computer Science, The University of Queensland(电气工程与计算机科学学院,昆士兰大学)
EviCast: Forecasting Retrieval Gains Through Shared Response Calibration
Lanzhou University(兰州大学);Nanjing University of Science and Technology(南京理工大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);Huawei(华为);Hefei University of Technology(合肥工业大学)
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)
From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室);University of Science and Technology of China(中国科学技术大学);College of Intelligence and Computing(智能科学与计算学院);iFLYTEK Research(iFLYTEK研究院)
Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting
The Hong Kong Polytechnic University(香港理工大学);Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波东方理工大学数字孪生研究院);Stockholm University(斯德哥尔摩大学)
ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting
Department of Computer Science and Engineering, Shahid Beheshti University, Iran(伊朗谢赫·贝赫什提大学计算机科学与工程系);School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran(伊朗基础科学研究院(IPM)计算机科学学院)
VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心);Amap, Alibaba Group(阿里巴巴集团阿地图);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院);Environmental Microbiome and Innovative Genomics Laboratory, Peking University(北京大学环境微生物与创新基因组实验室)
xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
AI & ML Group, TU Darmstadt(AI与机器学习小组,德累斯顿理工大学);TU Eindhoven(埃因霍温理工大学);Hessian Center for AI (hessian.AI)(黑森人工智能中心);German Research Center for AI (DFKI)(德国人工智能研究中心);Centre for Cognitive Science, TU Darmstadt(认知科学中心,德累斯顿理工大学)