Pattern recognition is a fundamental task in continuous sensing applications, but real-world scenarios often experience distribution shifts that necessitate learning generalizable representations for such tasks. This challenge is exacerbated with time-series data, which also exhibit inherent nonstationarity--variations in statistical and spectral properties over time. In this work, we offer a fresh perspective on learning generalizable representations for time-series classification by considering the phase information of a signal as an approximate proxy for nonstationarity and propose a phase-driven generalizable representation learning framework for time-series classification, PhASER. It consists of three key elements: 1) Hilbert transform-based augmentation, which diversifies nonstationarity while preserving task-specific discriminatory semantics, 2) separate magnitude-phase encoding, viewing time-varying magnitude and phase as independent modalities, and 3) phase-residual feature broadcasting, integrating 2D phase features with a residual connection to the 1D signal representation, providing inherent regularization to improve distribution-invariant learning. Extensive evaluations on five datasets from sleep-stage classification, human activity recognition, and gesture recognition against 13 state-of-the-art baseline methods demonstrate that PhASER consistently outperforms the best baselines by an average of 5% and up to 11% in some cases. Additionally, the principles of PhASER can be broadly applied to enhance the generalizability of existing time-series representation learning models.
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Guangdong University（广东大学）；Carnegie Mellon University（卡内基梅隆大学）；Shantou University（汕头大学）
Koopman-theoretic Approach for Identification of Exogenous Anomalies in Nonstationary Time-series Data
University of Washington（华盛顿大学）；NASA Global Modeling and Assimilation Office, Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心全球建模与同化办公室）；Morgan State University（摩根州立大学）
在许多情况下，有必要通过时间序列观测来监测复杂系统，并确定异常外源事件何时发生，以便采取相关行动。确定当前观察结果是否异常具有挑战性。它需要从历史数据中学习动态的外推概率模型，并使用有限数量的当前观测进行分类。我们利用长期概率预测的最新进展，即{ \em Deep ProbabilityKoopman}，建立一个通用的方法来分类多维时间序列数据中的异常。我们还展示了如何利用模型与域知识的动态，以减少I型和II型错误。我们证明了我们提出的方法对全球大气污染监测的重要现实世界的任务，将其与美国宇航局的全球地球系统模型。该系统成功检测到因COVID-19封锁和野火等事件而导致的局部空气质量异常。
Exponential inequalities for nonstationary Markov Chains
CREST, ENSAE, Université Paris Saclay（巴黎萨克雷大学国立统计与经济行政学院 CREST）；AGM UMR8088 University Paris-Seine（巴黎塞纳大学 AGM UMR8088）；CIMFAV, Universidad de Valparaiso（瓦尔帕莱索大学 CIMFAV）；CAM, Tianjin University（天津大学 CAM）
Data-driven detrending of nonstationary fractal time series with echo state networks
SAPIENZA University of Rome（罗马第一大学）；University of Tromsø - The Arctic University of Norway（特罗姆瑟大学-挪威北极大学）；University of Exeter（埃克塞特大学）；Ryerson University（瑞尔森大学）
Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction
National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University（东北大学工业智能与系统优化国家级前沿科学中心）；De Montfort University（德蒙福特大学）；Innovative Artificial Intelligence Cluster, Digital Future Institute, De Montfort University（德蒙福特大学数字未来研究所创新人工智能集群）；Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education（东北大学智能工业数据解析与优化教育部重点实验室）
Locally Linear Continual Learning for Time Series based on VC-Theoretical Generalization Bounds
Department of Electronic Engineering, Universidade Federal de Minas Gerais（米纳斯格拉斯联邦大学电子工程系）；Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais（米纳斯格拉斯联邦大学电气工程研究生项目）
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
McGill University（麦吉尔大学）；Mila - Quebec AI Institute（魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；University of Toronto（多伦多大学）；Concordia University（康科迪亚大学）；com（42.com）
FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting
Julius-Maximilians-Universität Würzburg, Modeling and Simulation Lab（乌尔姆-马克斯·普朗克大学，建模与仿真实验室）；Weihenstephan-Triesdorf University of Applied Sciences, Smart Farming（魏因施泰因-特里尔夫应用科学大学，智能农业）；Weihenstephan-Triesdorf University of Applied Sciences, Digital Energy Transition（魏因施泰因-特里尔夫应用科学大学，数字能源转型）
TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
Columbia University（哥伦比亚大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Yale University（耶鲁大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Google（谷歌）；University of Virginia（弗吉尼亚大学）
Application of time-series quantum generative model to financial data
Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究科）；Department of Physics, Tokyo Institute of Technology（东京工业大学物理系）；Sigma-i Co., Ltd.（Sigma-i有限公司）；Nomura Asset Management Co., Ltd.（野村资产管理有限公司）
