mlsanityData to 7 Oct 2026

AdaRNN: Adaptive Learning and Forecasting of Time Series

arXiv 2108.04443 ↗First posted 10 Aug 2021cs.LG cs.AIcited by 120

Not on the map. Why?

Abstract (arXiv)

Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes temporally, which will cause severe distribution shift problem to existing methods. However, it remains unexplored to model the time series in the distribution perspective. In this paper, we term this as Temporal Covariate Shift (TCS). This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data. AdaRNN is sequentially composed of two novel algorithms. First, we propose Temporal Distribution Characterization to better characterize the distribution information in the TS. Second, we propose Temporal Distribution Matching to reduce the distribution mismatch in TS to learn the adaptive TS model. AdaRNN is a general framework with flexible distribution distances integrated. Experiments on human activity recognition, air quality prediction, and financial analysis show that AdaRNN outperforms the latest methods by a classification accuracy of 2.6% and significantly reduces the RMSE by 9.0%. We also show that the temporal distribution matching algorithm can be extended in Transformer structure to boost its performance.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

26 of 57 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  4. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  6. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  8. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  9. 2013Domain Generalization via Invariant Feature Representationcited by 622
  10. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  11. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  12. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
14 more
  1. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  2. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  3. 2015Imaging Time-Series to Improve Classification and Imputationcited by 85
  4. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  5. 2019Shape and Time Distortion Loss for Training Deep Time Series Forecasting Modelscited by 66
  6. 2018Transfer learning for time series classificationcited by 60
  7. 2017Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Datacited by 47
  8. 2019Transfer Learning with Dynamic Distribution Adaptationcited by 40
  9. 2019Transfer Learning with Dynamic Adversarial Adaptation Networkcited by 37
  10. 2017Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networkscited by 30
  11. 2020Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversitycited by 9
  12. 2019Transfer Learning for Sequence Labeling Using Source Model and Target Datacited by 8
  13. 2018Transfer Learning for Clinical Time Series Analysis using Recurrent Neural Networkscited by 5
  14. 2019Transfer Learning for Sequences via Learning to Collocatecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 27; 2024: 36; 2025: 31; 2026: 13.

120 papers.

Sort:

By area:

  1. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  2. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  3. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  4. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  5. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 91
  6. 2022Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practicescited by 54
  7. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  8. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  9. 2024Frequency Adaptive Normalization For Non-stationary Time Series Forecastingcited by 45
  10. 2022Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfercited by 43
  11. 2024Retrieval Augmented Time Series Forecastingcited by 40
  12. 2025ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLMcited by 36
38 more
  1. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  2. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 30
  3. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 29
  4. 2022GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalizationcited by 28
  5. 2024Domain Generalization through Meta-Learning: A Surveycited by 28
  6. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 26
  7. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  8. 2025Non-stationary Diffusion For Probabilistic Time Series Forecastingcited by 24
  9. 2023Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shiftcited by 23
  10. 2023Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bankcited by 22
  11. 2023DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecastingcited by 21
  12. 2023Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detectioncited by 20
  13. 2023Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptationcited by 19
  14. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18
  15. 2024Proactive Model Adaptation Against Concept Drift for Online Time Series Forecastingcited by 18
  16. 2024Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generationcited by 14
  17. 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecastingcited by 14
  18. 2024Continuous Temporal Domain Generalizationcited by 14
  19. 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalizationcited by 12
  20. 2024Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecastingcited by 11
  21. 2024Prompt-Based Spatio-Temporal Graph Transfer Learningcited by 9
  22. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  23. 2025Gradient-Guided Annealing for Domain Generalizationcited by 9
  24. 2022Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworkscited by 8
  25. 2023Context-aware Domain Adaptation for Time Series Anomaly Detectioncited by 8
  26. 2023A Co-training Approach for Noisy Time Series Learningcited by 8
  27. 2024HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecastingcited by 8
  28. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
  29. 2024Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecastingcited by 7
  30. 2024Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenariocited by 7
  31. 2025MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Modelscited by 7
  32. 2022DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shiftcited by 6
  33. 2023Traffic Prediction with Transfer Learning: A Mutual Information-based Approachcited by 6
  34. 2023MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptationcited by 6
  35. 2024IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecastingcited by 6
  36. 2024Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecastingcited by 6
  37. 2023Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Predictioncited by 5
  38. 2024Structural Knowledge Informed Continual Multivariate Time Series Forecastingcited by 5

50 most cited of 120 All 120 (JSON)