Out-of-Distribution Generalization in Time Series

Overview

A list of research papers on out-of-distribution (OOD) generalization in time series. Existing studies categorize the problem from three key perspectives: data distribution, representation learning, and OOD evaluation. For more details, please refer to our survey paper, “Out-of-Distribution Generalization in Time Series: A Survey.”

Data Distribution

Real-world data distributions are often dynamic rather than static and frequently subject to various distribution shifts that challenge the assumptions made during training. Two common distribution shifts are covariate shift and concept Drift.

Covariate Shift

[ICML 2022] Time Series Prediction under Distribution Shift using Differentiable Forgetting [Paper] [Code]
[ICLR 2022] Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift [Paper] [Code]
[SMC 2022] Feature Importance Identification for Time Series Classifiers [Paper]
[ICPADS 2022] Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks [Paper][Code]
[MM 2022] Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift [Paper][Code]
[FUZZ 2023] An Initial Step Towards Stable Explanations for Multivariate Time Series Classifiers with LIME [Paper]
[Inf. Sci. 2023] Explaining Time Series Classifiers through Meaningful Perturbation and Optimisation [Paper] [Code]
[J.Neunet 2024] SEGAL Time Series Classification - Stable Explanations Using A Generative Model and An Adaptive Weighting Method for LIME [Paper]
[VR 2024] Generating Virtual Reality Stroke Gesture Data from Out-of-Distribution Desktop Stroke Gesture Data [Paper] [Code]
[AAAI 2024] Generalizing across Temporal Domains with Koopman Operators [Paper] [Code]
[IJCAI 2024] Temporal Domain Generalization via Learning Instance-level Evolving Patterns [Paper] [Code]
[ICML 2024] Connect later: Improving fine-tuning for robustness with targeted augmentations [Paper] [Code]
[ICML 2024] TimeX++: Learning Time-Series Explanations with Information Bottleneck [Paper] [Code]
[TNNLS 2025] Robust Multivariate Time Series Forecasting Against Intraseries and Interseries Transitional Shift [Paper]
[TMLR 2025] Batch Training for Streaming Time Series: A Transferable Augmentation Framework to Combat Distribution Shifts [Paper]
[KDD 2025] IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting [Paper] [Code]

Concept Drift

[ICTAI 2017] Time Series Forecasting in the Presence of Concept Drift: A PSO-based Approach [Paper]
[AAAI 2019] Cogra: Concept-Drift-Aware Stochastic Gradient Descent for Time-Series Forecasting [Paper]
[TKDE 2022] A Hybrid Spiking Neurons Embedded LSTM Network for Multivariate Time Series Learning Under Concept-Drift Environment [Paper]
[NeurIPS 2022] Dynamic Graph Neural Networks Under Spatio-Temporal Distribution Shift [Paper] [Code]
[ICML 2023] Domain adaptation for time series under feature and label shifts [Paper] [Code]
[NeurIPS 2023] OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling [Paper] [Code]
[KDD 2023] Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning [Paper] [Code]
[TNNLS 2024] Distributional Drift Adaptation With Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting [Paper]
[SSRN 2024] Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts [Paper] [Code]
[ICLR 2024] Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference [Paper] [Code]
[ICML 2024] CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables [Paper] [Code]
[TCYB 2024] TS-DM: A Time Segmentation-Based Data Stream Learning Method for Concept Drift Adaptation [Paper] [Code]
[TPAMI 2024] Transferable Time-Series Forecasting Under Causal Conditional Shift [Paper] [Code]
[NeurIPS 2024] KAN4Drift: Are KAN Effective for Identifying and Tracking Concept Drift in Time Series? [Paper]
[KDD 2024] Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift [Paper] [Code]
[Neucom. 2025] TD-IVDM: A multi-scale concept drift detection method for time series forecasting tasks [Paper]
[ArXiv 2025] Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting [Paper] [Code]
[TKDE 2025] Long-Term Urban Flow Prediction Against Data Distribution Shift: A Causal Perspective [Paper] [Code]
[NeurIPS 2025] Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift [Paper] [Code]
[NeurIPS 2025] How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning [Paper] [Code]
[KDD 2025] Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting [Paper] [Code]
[KDD 2025] MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecastin [Paper] [Code]

Representation learning

Representation learning enhances generalization by extracting robust and generalizable features. These methods can be categorized into five groups: decoupling-based methods, invariance-based methods, ensemble-based learning, adaptive mechanism-based methods, and large time-series models.

Decoupling-based Methods

[NeurIPS 2020] Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests [Paper] [Code]
[ICML 2022] FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting [Paper] [Code]
[NeurIPS 2022] Dynamic Graph Neural Networks Under Spatio-Temporal Distribution Shift [Paper] [Code]
[ICRA 2022] Causal-based Time Series Domain Generalization for Vehicle Intention Prediction [Paper]
[ICC 2023] Out-of-distribution Internet Traffic Prediction Generalization Using Deep Sequence Model [Paper]
[KDD 2023] Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning [Paper] [Code]
[ICML 2023] Neural Stochastic Differential Games for Time-series Analysis [Paper] [Code]
[Sci. Robot. 2023] Robust Flight Navigation Out of Distribution with Liquid Neural Networks [Paper] [Code]
[KDD 2024] Orthogonality Matters: Invariant Time Series Representation for Out-of-distribution Classification [Paper] [Code]
[TKDE 2024] Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting [Paper] [Code]
[AAAI 2024] MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting [Paper] [Code]
[MM 2024] Spatio-temporal Heterogeneous Federated Learning for Time Series Classification with Multi-view Orthogonal Training [Paper]
[TPAMI 2024] Transferable Time-Series Forecasting Under Causal Conditional Shift [Paper]
[Inf. Sci. 2024] A Causal Representation Learning Based Model for Time Series Prediction under External Interference [Paper] [Code]
[ICML 2024] CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables [Paper] [Code]
[TPAMI 2024] Transferable Time-Series Forecasting Under Causal Conditional Shift [Paper] [Code]
[Neucom. 2025] TD-IVDM: A multi-scale concept drift detection method for time series forecasting tasks [Paper]
[KDD 2025] IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting [Paper] [Code]
[TKDE 2025] Long-Term Urban Flow Prediction Against Data Distribution Shift: A Causal Perspective [Paper] [Code]
[TNNLS 2025] Robust Multivariate Time Series Forecasting Against Intraseries and Interseries Transitional Shift [Paper]
[KDD 2025] MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecastin [Paper] [Code]

Invariant-based Methods

[ICLR 2021] In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness [Paper] [Code]
[AAAI 2021] Latent independent excitation for generalizable sensor-based cross-person activity recognition [Paper] [Code]
[AAAI 2021] Meta-learning Framework with Applications to Zero-shot Time-series Forecasting [Paper] [Code]
[MM 2022] Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift [Paper][Code]
[ICRA 2023] Robust Forecasting for Robotic Control: A Game-Theoretic Approach [Paper]
[KDD 2023] DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting [Paper] [Code]
[KDD 2023] TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting [Paper] [Code]
[NeurIPS 2023] Evolving Standardization for Continual Domain Generalization over Temporal Drift [Paper] [Code]
[ICDM 2023] Boosting Urban Prediction via Addressing Spatial-Temporal Distribution Shift [Paper]
[ICLR 2023] Out-of-distribution Representation Learning for Time Series Classification [Paper] [Code]
[ICML 2023] Domain adaptation for time series under feature and label shifts [Paper] [Code]
[AAAI 2023] Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting [Paper] [Code]
[WWW 2024] Towards Invariant Time Series Forecasting in Smart Cities [Paper] [Video]
[ICML 2024] Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning [Paper] [Code]
[ACM TKDD 2024]Domain Generalization in Time Series Forecasting [Paper] [Code]
[ICLR 2025] Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization [Paper] [Code]
[TNNLS 2024] Distributional Drift Adaptation With Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting [Paper]
[VR 2024] Generating Virtual Reality Stroke Gesture Data from Out-of-Distribution Desktop Stroke Gesture Data [Paper] [Code]
[AAAI 2024] Generalizing across Temporal Domains with Koopman Operators [Paper] [Code]
[ICML 2024] Connect later: Improving fine-tuning for robustness with targeted augmentations [Paper] [Code]
[NeurIPS 2024] Continuous Temporal Domain Generalization [Paper] [Code]
[TPAMI 2024] Diversify: A General Framework for Time Series Out-of-Distribution Detection and Generalization [Paper] [Code]
[DAC 2024] SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification [Paper] [PPT]
[NeurIPS 2025] Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift [Paper] [Code]

Adaptive Mechanism-based Methods

[ICTAI 2017] Time Series Forecasting in the Presence of Concept Drift: A PSO-based Approach [Paper]
[AAAI 2019] Cogra: Concept-Drift-Aware Stochastic Gradient Descent for Time-Series Forecasting [Paper]
[TKDE 2022] A Hybrid Spiking Neurons Embedded LSTM Network for Multivariate Time Series Learning Under Concept-Drift Environment [Paper]
[ICML 2022] Time Series Prediction under Distribution Shift using Differentiable Forgetting [Paper] [Code]
[ICPADS 2022] Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks [Paper][Code]
[TCYB 2024] TS-DM: A Time Segmentation-Based Data Stream Learning Method for Concept Drift Adaptation [Paper] [Code]
[SSRN 2024] Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts [Paper] [Code]
[NeurIPS 2024] KAN4Drift: Are KAN Effective for Identifying and Tracking Concept Drift in Time Series? [Paper]
[KDD 2024] Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift [Paper] [Code]
[ArXiv 2025] Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting [Paper] [Code]
[JMLR 2024] Conformal Inference for Online Prediction with Arbitrary Distribution Shifts [Paper] [Code]
[TMLR 2025] Batch Training for Streaming Time Series: A Transferable Augmentation Framework to Combat Distribution Shifts [Paper]
[NeurIPS 2025] How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning [Paper] [Code]
[NeurIPS 2023] OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling [Paper] [Code]
[KDD 2025] Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting [Paper] [Code]

Large Time-Series Models

[NeurIPS 2023] ForecastPFN: Synthetically-Trained Zero-Shot Forecasting [Paper] [Code]
[EACL 2023] Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models? [Paper] [Code]
[NeurIPS 2024] Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-shot Forecasting of Multivariate Time Series [Paper] [Code]
[NeurIPS 2023] JoLT: Jointly Learned Representations of Language and Time-Series [Paper]
[NeurIPS 2023] One Fits All: Power General Time Series Analysis by Pretrained LM [Paper] [Code]
[R0-FoMo 2023] Lag-Llama: Towards Foundation Models for Time Series Forecasting [Paper] [Code]
[NeurIPS 2023] Large Language Models Are Zero-Shot Time Series Forecasters [Paper] [Code]
[ArXiv 2023] Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain [Paper] [Code]
[ArXiv 2023] TimeGPT-1 [Paper] [Code]
[ICASSP 2024] ETP: Learning Transferable ECG Representations via ECG-Text Pre-Training [Paper]
[AAAI 2024] JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract) [Paper]
[ICLR 2024] Time-LLM: Time Series Forecasting by Reprogramming Large Language Models [Paper] [Code]
[ICML 2024] Unified Rraining of Universal Time Series Forecasting Transformers [Paper] [Code]
[CIKM 2024] General Time Transformer: an Encoder-only Foundation Model for Zero-Shot Multivariate Time Series Forecasting [Paper] [Code]
[NeurIPS 2024] Align and Fine-Tune: Enhancing LLMs for Time-Series Forecasting [Paper]
[NeurIPS 2024] Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization [Paper]
[ICML 2024] MOMENT: A Family of Open Time-series Foundation Models [Paper] [Code]
[ICML 2024] Timer: Generative Pre-trained Transformers Are Large Time Series Models [Paper] [Code]
[ICML 2024] A Decoder-only Foundation Model for Time-series Forecasting [Paper] [Code]
[TMLR 2024] Chronos: Learning the Language of Time Series [Paper] [Code]
[ICLR 2025] Towards Neural Scaling Laws for Time Series Foundation Models [Paper] [Code]
[AAAI 2025] ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data [Paper] [Code]
[AAAI 2025] CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning [Paper] [Code]
[CIKM 2025] TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models [Paper] [Code]
[TKDE 2025] TimeRAF: Retrieval-Augmented Foundation Model for Zero-Shot Time Series Forecasting [Paper]

Time Series Datasets 📊

📌 General Time Series

💾 UEA Classification – A rich set of time series datasets for classification tasks.
📊 UCR Archive – Benchmark datasets for time series research.

💰 Economy & Finance

📈 PPA Dataset – Causal inference data for Power Purchase Agreements.
💹 Exchange Rate – Historical exchange rates for financial forecasting.

🚗 Transportation

🛣 SIP Traffic – Traffic data from Suzhou Industrial Park.
🚌 METR-LA – Los Angeles traffic sensor data.
✈️ Flight Data – Aircraft trajectory & air traffic. data.
🚦 Traffic Flow – Multi-city traffic congestion datasets.

⚡ Energy & Environment

🔋 Electricity Load – Power consumption data for energy forecasting.
☀️ Solar Energy – Solar power generation datasets.
🌦 Weather & ETT – Meteorological time series for climate analysis.

🌫 Air Quality

🌍 KnowAir PM2.5 – Air pollution dataset focusing on PM2.5 levels.

🏥 Health & Medicine

🦾 EMG - Electromyography dataset records muscle activity.

⌚️ Human Activity Recognition

🏃🏻‍♀️ UCIHAR - Smartphone-based human activity recognition dataset.
🩼 UniMiB-SHAR - Smartphone-based human activity recognition and fall detection dataset.
📱 Opportunity - Multiple wearable and environmental sensors for human activity recognition dataset.

🛠 More Datasets

📚 Multivariate Time Series – Traffic, electricity, solar, and financial datasets.

[ArXiv 2021] Towards Out-of-Distribution Generalization: A Survey [Paper]
[ArXiv 2022] Out-of-Distribution Generalization on Graphs: A Survey [Paper]
[EMNLP 2023] Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future [Paper]
[TPAMI 2024] Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects [Paper]
[TPAMI 2024] A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection [Paper]
[TKDE 2024] A Survey on Time-Series Pre-Trained models [Paper]
[TMLR 2024] WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series [Paper]

Acknowledgement

Last updated on October 18, 2025. (For problems, contact xinwu5386@gmail.com. To add papers, please pull request at our repo)