mlsanityData to 7 Oct 2026

Continual Learning for non-stationary regression via Memory-Efficient Replay

arXiv 2602.09720 ↗First posted 10 Feb 2026stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by continual learning (CL), which allows systems to gradually acquire knowledge without incurring the prohibitive costs of retraining them from scratch. Most research on continual learning focuses on classification problems, while very few studies address regression tasks. We propose the first prototype-based generative replay framework designed for online task-free continual regression. Our approach defines an adaptive output-space discretization model, enabling prototype-based generative replay for continual regression without storing raw data. Evidence obtained from several benchmark datasets shows that our framework reduces forgetting and provides more stable performance than other state-of-the-art solutions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 10 Feb 2026.

Builds on

24 of 39 references.

References · 24

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2017Continual Learning with Deep Generative Replaycited by 1,152
  4. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  5. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  6. 2022How catastrophic can catastrophic forgetting be in linear regression?cited by 80
  7. 2023Maintaining Plasticity in Continual Learning via Regenerative Regularizationcited by 63
  8. 2024SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detectioncited by 42
  9. 2019A Unifying Bayesian View of Continual Learningcited by 38
  10. 2021Continually Learning Self-Supervised Representations with Projected Functional Regularizationcited by 38
  11. 2023Avalanche: A PyTorch Library for Deep Continual Learningcited by 33
  12. 2024A Statistical Theory of Regularization-Based Continual Learningcited by 32
12 more
  1. 2024Understanding Forgetting in Continual Learning with Linear Regressioncited by 26
  2. 2022Task-Free Continual Learning via Online Discrepancy Distance Learningcited by 22
  3. 2021CLeaR: An Adaptive Continual Learning Framework for Regression Taskscited by 21
  4. 2019BooVAE: Boosting Approach for Continual Learning of VAEcited by 18
  5. 2025MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classificationcited by 8
  6. 2024Continual Learning with Diffusion-based Generative Replay for Industrial Streaming Datacited by 6
  7. 2024Certified Continual Learning for Neural Network Regressioncited by 5
  8. 2024Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approachcited by 5
  9. 2024CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networkscited by 4
  10. 2025Global Convergence of Continual Learning on Non-IID Datacited by 3
  11. 2025Continual Learning Strategies for 3D Engineering Regression Problems: A Benchmarking Studycited by 3
  12. 2021Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecastscited by 2

Built on by

Not cited yet.