Do Neural Networks Lose Plasticity in a Gradually Changing World?
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911436814417920 |
|---|---|
| author | Liu, Tianhui Mou, Lili |
| author_facet | Liu, Tianhui Mou, Lili |
| contents | Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks gradually losing the ability to learn new tasks. However, existing plasticity research largely relies on contrived settings with abrupt task transitions, which often do not reflect real-world environments. In this paper, we propose to investigate a gradually changing environment, and we simulate this by input/output interpolation and task sampling. We perform theoretical and empirical analysis, showing that the loss of plasticity is an artifact of abrupt tasks changes in the environment and can be largely mitigated if the world changes gradually. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09234 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Do Neural Networks Lose Plasticity in a Gradually Changing World? Liu, Tianhui Mou, Lili Machine Learning Artificial Intelligence Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks gradually losing the ability to learn new tasks. However, existing plasticity research largely relies on contrived settings with abrupt task transitions, which often do not reflect real-world environments. In this paper, we propose to investigate a gradually changing environment, and we simulate this by input/output interpolation and task sampling. We perform theoretical and empirical analysis, showing that the loss of plasticity is an artifact of abrupt tasks changes in the environment and can be largely mitigated if the world changes gradually. |
| title | Do Neural Networks Lose Plasticity in a Gradually Changing World? |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.09234 |