mlsanityData to 14 Oct 2026

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

arXiv 2309.12659 ↗First posted 22 Sep 2023cs.LG cs.DScited by 74

Not on the map. Why?

Abstract (arXiv)

Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms are designed for online time series forecasting, with some exploiting cross-variable dependency while others assume independence among variables. Given every data assumption has its own pros and cons in online time series modeling, we propose Online ensembling Network (OneNet). It dynamically updates and combines two models, with one focusing on modeling the dependency across the time dimension and the other on cross-variate dependency. Our method incorporates a reinforcement learning-based approach into the traditional online convex programming framework, allowing for the linear combination of the two models with dynamically adjusted weights. OneNet addresses the main shortcoming of classical online learning methods that tend to be slow in adapting to the concept drift. Empirical results show that OneNet reduces online forecasting error by more than 50% compared to the State-Of-The-Art (SOTA) method. The code is available at urlhttps://github.com/yfzhang114/OneNet.

Key facts. Cited by 74 papers in the map (data through 14 Oct 2026). Builds on 36 of its 71 references that are in the map. First posted on arXiv 22 Sep 2023.

Builds on

36 of 71 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  6. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  11. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  12. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
24 more
  1. 2021Domain Generalization: A Surveycited by 764
  2. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 590
  3. 2022Transformers in Time Series: A Surveycited by 497
  4. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  5. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
  6. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  7. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  8. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  9. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 231
  10. 2018Task-Free Continual Learningcited by 221
  11. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
  12. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  13. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  14. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  15. 2021Gated Transformer Networks for Multivariate Time Series Classificationcited by 58
  16. 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
  17. 2022Learning Fast and Slow for Online Time Series Forecastingcited by 45
  18. 2020How to Retrain Recommender System? A Sequential Meta-Learning Methodcited by 42
  19. 2022DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptationcited by 36
  20. 2013Online Learning for Time Series Predictioncited by 33
  21. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  22. 2019Exponentiated Gradient Meets Gradient Descentcited by 32
  23. 2021Learning Domain Invariant Representations for Generalizable Person Re-Identificationcited by 22
  24. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 21; 2025: 21; 2026: 32.

74 papers.

Sort:

By area:

  1. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 70
  2. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 27
  3. 2024Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shiftcited by 24
  4. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysiscited by 22
  5. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  6. 2024Proactive Model Adaptation Against Concept Drift for Online Time Series Forecastingcited by 19
  7. 2025Lightweight Online Adaption for Time Series Foundation Model Forecastscited by 16
  8. 2025Out-of-Distribution Generalization in Time Series: A Surveycited by 16
  9. 2025Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learningcited by 14
  10. 2024Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adaptcited by 13
  11. 2024Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspectivecited by 13
  12. 2026The Forecast After the Forecast: A Post-Processing Shift in Time Seriescited by 10
38 more
  1. 2025Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecastingcited by 9
  2. 2026Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Modelscited by 9
  3. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  4. 2024Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenariocited by 7
  5. 2024Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Datacited by 6
  6. 2024A Novel Hyperdimensional Computing Framework for Online Time Series Forecasting on the Edgecited by 5
  7. 2024Structural Knowledge Informed Continual Multivariate Time Series Forecastingcited by 5
  8. 2026TS-Memory: Plug-and-Play Memory for Time Series Foundation Modelscited by 5
  9. 2026Towards Principled Test-Time Adaptation for Time Series Forecastingcited by 5
  10. 2024Towards Foundation Time Series Model: To Synthesize Or Not To Synthesize?cited by 4
  11. 2025From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Educationcited by 4
  12. 2025Online time series prediction using feature adjustmentcited by 4
  13. 2024LogoRA: Local-Global Representation Alignment for Robust Time Series Classificationcited by 3
  14. 2025Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecastingcited by 3
  15. 2025Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecastingcited by 3
  16. 2024Partial-Multivariate Model for Forecastingcited by 2
  17. 2024Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shiftscited by 2
  18. 2025RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budgetcited by 2
  19. 2025Multi-grained spatial-temporal feature complementarity for accurate online cellular traffic predictioncited by 2
  20. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
  21. 2025Online Time Series Forecasting with Theoretical Guaranteescited by 2
  22. 2026TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Seriescited by 2
  23. 2024Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shiftcited by 1
  24. 2024Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequencescited by 1
  25. 2024Distribution-aware Online Continual Learning for Urban Spatio-Temporal Forecastingcited by 1
  26. 2025Tackling Time-Series Forecasting Generalization via Mitigating Concept Driftcited by 1
  27. 2025DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecastingcited by 1
  28. 2026Momentum LMS Theory beyond Stationarity: Stability, Tracking, and Regretcited by 1
  29. 2026Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Predictioncited by 1
  30. 2026Dynamic Multi-period Experts for Online Time Series Forecastingcited by 1
  31. 2026INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regressioncited by 1
  32. 2026PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecastingcited by 1
  33. 2026On-Device Adaptive Battery Power Prediction for Electric Vehiclescited by 1
  34. 2026Compositional Spectral Prompts for LLM-based Online Time Series Forecastingcited by 1
  35. 2026CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learningcited by 1
  36. 2024StreamFP: Learnable Fingerprint-guided Data Selection for Efficient Stream Learningcited by 0
  37. 2024Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradientcited by 0
  38. 2024WormKAN: Are KAN Effective for Identifying and Tracking Concept Drift in Time Series?cited by 0

50 most cited of 74 All 74 (JSON)