Continual Learning for non-stationary regression via Memory-Efficient Replay
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918331134509056 |
|---|---|
| author | García-Santaclara, Pablo Fernández-Castro, Bruno Díaz-Redondo, RebecaP. Alonso-Gamarra, Martín |
| author_facet | García-Santaclara, Pablo Fernández-Castro, Bruno Díaz-Redondo, RebecaP. Alonso-Gamarra, Martín |
| contents | 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 Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09720 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Continual Learning for non-stationary regression via Memory-Efficient Replay García-Santaclara, Pablo Fernández-Castro, Bruno Díaz-Redondo, RebecaP. Alonso-Gamarra, Martín Machine Learning 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 Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data.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. |
| title | Continual Learning for non-stationary regression via Memory-Efficient Replay |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.09720 |