Time Series Data Augmentation

Ask about this topic

Overview

Time series data augmentation creates additional or varied sequential examples to help models learn when labeled data are scarce, noisy, or unevenly distributed. Approaches range from transformations such as noise, time warping, shifting, and subsequence sampling to GAN, VAE, and diffusion-based generation; some also build augmented views for contrastive learning or self-distillation. Methods are tested across forecasting, classification, anomaly detection, and applications such as clinical signals, finance, and robot demonstrations, with success usually judged by downstream task performance. A central tension is that more varied data can improve robustness but can also distort temporal dynamics or hurt particular architectures, so useful augmentation must preserve relevant structure and be evaluated for its intended model and setting.

Latest papers

CardsList

28 papers5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

  1. Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning

    Oct 19, 2026Shuyuan Hu, Deng-Ke Wu, Yifan Jin +4Robot Imitation LearningBimanual Robotic Manipulation

    School of AI, Shanghai Jiao Tong University · Central South University · South China Normal University +1

  2. RESTA: Time-Scaling Augmentation for Data-Efficient Robot Imitation Learning

    Oct 13, 2026Yunpeng Jiang, Jianshu Hu, Han Fang +3Data-Efficient Robot LearningRobot Imitation Learning

    Global College, Shanghai Jiao Tong University, Shanghai, China · Shanghai Institute of Physical Intelligence and Robotics (PAIR), Shanghai, China · Duke Kunshan University, Jiangsu, China

  3. Image Synthesis as an Intermediate for Controllable Time Series Generation

    Oct 4, 2026Haochen Yuan, Jing Xie, Yunbo WangTime Series ForecastingTime Series Generation

    MoE Key Lab of Artificial Intelligence, Institute of AI, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

  4. WinoTS: Wavelet-based Self-Distillation for Time Series Models

    Sep 30, 2026Noam Major, Kathy Razmadze, Yoli ShavitSelf-Supervised Time Series Representation LearningTime Series Data Augmentation

    Bar-Ilan University, Ramat-Gan, Israel

  5. An Effective, Reliable, and Robust Framework for Human Activity Recognition Using Wearable Sensors

    Sep 29, 2026Nafees Ahmad, Ho-fung Leung, Muhammad Adil Abid +1Human Activity RecognitionWearable Sensing

    The Chinese University of Hong Kong, China · Independent Researcher, China · Malmö University, Sweden +1

  6. SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning

    Sep 26, 2026Yi Tang, Tengxue Zhang, Yang Shu +3Time-Series Foundation ModelsTime Series Forecasting

    East China Normal University, Shanghai, China · Chang’an University, Xi’an, China

  7. Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling

    Sep 14, 2026Rafael Pina, Varuna De Silva, Mindula IlleperumaSynthetic Data AugmentationTime Series Generation

    Institute for Digital Technologies Loughborough University London London, United Kingdom

  8. DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning

    Sep 9, 2026Wenrui Xu, Anas Enanaa, Keshab K. ParhiEEG Seizure DetectionRepresentation Learning

    University of Minnesota, Twin Cities

  9. Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning

    Aug 17, 2026Serena Su, Yifan Wang, Senwei LiangInterpretable MLTime Series Data Augmentation

    Department of Mathematics & Statistic, Texas Tech University, Lubbock, 79407, Texas, USA

  10. Not All EEG Moments Are Equal: Position-Adaptive Time Scheduling for EEG Generation

    Jul 25, 2026Boheng Liu, Ziyu Li, Chenghua Duan +2Brain-Computer InterfacesEEG Signal Generation

    School of Computer Science and Technology Beijing Institute of Technology Beijing, China

  11. Learning by Shifting: Temporal View Construction for Time Series Contrastive Learning

    Jun 20, 2026Abdul-Kazeem Shamba, Kerstin Bach, Gavin TaylorContrastive LearningTime Series Classification

    Norwegian University of Science and Technology, Norway · United States Naval Academy, USA

  12. Robust Transformer-Based One-Step Stock Index Forecasting via Shifted Data Augmentation

    Jun 14, 2026Tien Thanh ThachTime Series ForecastingTime Series Data Augmentation

    Faculty of Mathematics and Statistics, Ton Duc Thang University, Ho Chi Minh City, Vietnam

  13. A Systematic Approach for Selecting Trajectories for Data Augmentation

    Jun 9, 2026Adam NordlingSynthetic Data AugmentationData Augmentation

  14. UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

    Jun 9, 2026Du Yin, Hao Xue, Jinliang Deng +4Constrained Generative ModelingTime Series Generation

    University of New South Wales Sydney, NSW, Australia · HKUST(GZ) China · BUAA Beijing, China

  15. A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection

    Jun 9, 2026Davood Fattahi, Runze Yan, Saurabh Kataria +2Atrial Fibrillation DetectionTime Series Data Augmentation

    Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA, USA · Department of Computer Science, Emory University, Atlanta, GA, USA · Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA +1

  16. TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation

    May 26, 2026Zesen Wang, Lijuan Lan, Yonggang Li +1Time Series GenerationTime Series Data Augmentation

    School of Automation, Central South University, Changsha, China

  17. fMRI-Diffusion: Generating fMRI Time Series Via a Temporal Transformer Diffusion Model for Major Depressive Disorder Diagnosis

    May 22, 2026Muhammad Asif Hasan, Yanming Zhu, Xuefei Yin +1Depression DetectionTime Series Generation

    aSchool of Information and Communication Technology, Griffith University, Gold Coast, QLD, 4215, Australia

  18. DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data

    May 18, 2026Masahiro Suzuki, Bohui Xia, Hiroto Yamamoto +1Time Series ForecastingTime Series Data Augmentation

    Sony Group Corporation Tokyo, Japan

  19. Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters

    May 7, 2026Hugo Cazaux, Eyjólfur Ingi Ásgeirsson, Hlynur StefánssonSynthetic Data AugmentationSynthetic Data Generation

    Department of Engineering Reykjavík University Iceland, Menntavegur 1, 102

  20. Preserving Temporal Dynamics in Time Series Generation

    Apr 29, 2026Ci Lin, Futong Li, Tet Yeap +1Time Series GenerationTime Series Data Augmentation

  21. IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation

    Apr 22, 2026Mingchun Sun, Rongqiang Zhao, Muhammad Abdul Munnaf +1Synthetic Data AugmentationData Augmentation

    Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China. · State Key Laboratory of Smart Farm Technologies and Systems, Harbin 150001, China. · Agricultural Biosystems Engineering, Wageningen University and Research, Wageningen 6703 CH, Netherlands.

  22. CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction

    Apr 16, 2026Honglin Guo, Rihao Chang, He Jiao +3Sepsis PredictionClinical Prediction

    Tianjin University, Tianjin 300072, China · Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310016, China · Tianjin Medical University General Hospital, Tianjin 300052, China

  23. Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting

    Apr 10, 2026Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr +1Multivariate Time Series ForecastingLong-Term Time Series Forecasting

    Data Science Group University of Hildesheim Hildesheim, Germany · Information Systems and Machine Learning Lab (ISMLL) University of Hildesheim Hildesheim, Germany

  24. SBBTS: A Unified Schrödinger-Bass Framework for Synthetic Financial Time Series

    Apr 8, 2026Alexandre Alouadi, Grégoire Loeper, Célian Marsala +2Time Series GenerationFinancial Time Series

    BNPP and Ecole Polytechnique. · BNPP and Monash University · BNPP and ENSAE Paris +2

  25. Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

    Mar 28, 2026Yun Tian, Guili Wang, Jian Bi +7RUL EstimationLithium-Ion Batteries

    School of Physics and Electronic Information, Anhui Normal University, Wuhu 241002, China · College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China · School of Design, NingboTech University, Ningbo 315100, China +2

  26. Financial time series augmentation using transformer based GAN architecture

    Feb 19, 2026Andrzej Podobiński, Jarosław A. ChudziakTime Series Data AugmentationFinancial Time Series

    Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland

  27. Benchmarking IoT Time-Series AD with Event-Level Augmentations

    Feb 17, 2026Dmitry Zhevnenko, Ilya Makarov, Aleksandr Kovalenko +6Time-Series Anomaly DetectionAnomaly Detection

    AXXX, Moscow, Russia · Research Center of the Artificial Intelligence Institute, Innopolis University, Innopolis, Russia · Trusted AI Center, RAS, Moscow, Russia +1

  28. L-GTA: Latent Generative Modeling for Time Series Augmentation

    Jul 31, 2025Luis Roque, Vitor Cerqueira, Carlos Soares +1Variational AutoencodersSynthetic Data Augmentation

    Faculdade de Engenharia da Universidade do Porto, Porto, Portugal · University of Coimbra, Coimbra, Portugal · Fraunhofer Portugal AICOS, Portugal +1