# Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt

arXiv: https://arxiv.org/abs/2403.14949 · HTML: https://mlsanity.com/paper/2403.14949/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting](https://mlsanity.com/paper/1905.03806/) (2019)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder](https://mlsanity.com/paper/2003.02977/) (2020)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [Learning Fast and Slow for Online Time Series Forecasting](https://mlsanity.com/paper/2202.11672/) (2022)
- [DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation](https://mlsanity.com/paper/2201.04038/) (2022)
- [Online Learning for Time Series Prediction](https://mlsanity.com/paper/1302.6927/) (2013)
- [SIESTA: Efficient Online Continual Learning with Sleep](https://mlsanity.com/paper/2303.10725/) (2023)
- [Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder](https://mlsanity.com/paper/2205.07649/) (2022)
- [Model-free Test Time Adaptation for Out-Of-Distribution Detection](https://mlsanity.com/paper/2311.16420/) (2023)

## Built on by (most cited first, 13 of 13)

- [Lightweight Online Adaption for Time Series Foundation Model Forecasts](https://mlsanity.com/paper/2502.12920/) (2025)
- [Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models](https://mlsanity.com/paper/2606.14222/) (2026)
- [Online time series prediction using feature adjustment](https://mlsanity.com/paper/2509.03810/) (2025)
- [Multi-grained spatial-temporal feature complementarity for accurate online cellular traffic prediction](https://mlsanity.com/paper/2508.08281/) (2025)
- [Online Time Series Forecasting with Theoretical Guarantees](https://mlsanity.com/paper/2510.18281/) (2025)
- [Adapting Time Series Foundation Models through Data Mixtures](https://mlsanity.com/paper/2603.02840/) (2026)
- [Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Prediction](https://mlsanity.com/paper/2602.21757/) (2026)
- [Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration](https://mlsanity.com/paper/2605.28603/) (2026)
- [When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting](https://mlsanity.com/paper/2609.01126/) (2026)
- [Correction-space Cross-variate Interaction for Test-time Adaptation in Time Series Forecasting](https://mlsanity.com/paper/2609.34638/) (2026)
- [Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting](https://mlsanity.com/paper/2609.39789/) (2026)
- [AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams](https://mlsanity.com/paper/2610.02661/) (2026)
- [The Premise Is the Problem: Exchangeability Failure in Self-Monitored Test-Time Adaptation](https://mlsanity.com/paper/2610.07038/) (2026)

## Abstract (arXiv)

Online updating of time series forecasting models aims to tackle the challenge of concept drifting by adjusting forecasting models based on streaming data. While numerous algorithms have been developed, most of them focus on model design and updating. In practice, many of these methods struggle with continuous performance regression in the face of accumulated concept drifts over time. To address this limitation, we present a novel approach, Concept Drift Detection anD Adaptation (D3A), that first detects drifting conception and then aggressively adapts the current model to the drifted concepts after the detection for rapid adaption. To best harness the utility of historical data for model adaptation, we propose a data augmentation strategy introducing Gaussian noise into existing training instances. It helps mitigate the data distribution gap, a critical factor contributing to train-test performance inconsistency. The significance of our data augmentation process is verified by our theoretical analysis. Our empirical studies across six datasets demonstrate the effectiveness of D3A in improving model adaptation capability. Notably, compared to a simple Temporal Convolutional Network (TCN) baseline, D3A reduces the average Mean Squared Error (MSE) by 43.9%. For the state-of-the-art (SOTA) model, the MSE is reduced by 33.3%.