Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909820222701568 |
|---|---|
| author | Karaouli, Nouha Coquenet, Denis Fromont, Elisa Mermillod, Martial Reyboz, Marina |
| author_facet | Karaouli, Nouha Coquenet, Denis Fromont, Elisa Mermillod, Martial Reyboz, Marina |
| contents | Time Series Foundation Models (TSFMs) have shown promising zero-shot generalization across diverse forecasting tasks. However, their robustness to continual adaptation remains underexplored. In this work, we investigate the extent to which TSFMs suffer from catastrophic forgetting when fine-tuned sequentially on multiple datasets. Using synthetic datasets designed with varying degrees of periodic structure, we measure the trade-off between adaptation to new data and retention of prior knowledge. Our experiments reveal that, while fine-tuning improves performance on new tasks, it often causes significant degradation on previously learned ones, illustrating a fundamental stability-plasticity dilemma. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00809 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Are Time Series Foundation Models Susceptible to Catastrophic Forgetting? Karaouli, Nouha Coquenet, Denis Fromont, Elisa Mermillod, Martial Reyboz, Marina Machine Learning Time Series Foundation Models (TSFMs) have shown promising zero-shot generalization across diverse forecasting tasks. However, their robustness to continual adaptation remains underexplored. In this work, we investigate the extent to which TSFMs suffer from catastrophic forgetting when fine-tuned sequentially on multiple datasets. Using synthetic datasets designed with varying degrees of periodic structure, we measure the trade-off between adaptation to new data and retention of prior knowledge. Our experiments reveal that, while fine-tuning improves performance on new tasks, it often causes significant degradation on previously learned ones, illustrating a fundamental stability-plasticity dilemma. |
| title | Are Time Series Foundation Models Susceptible to Catastrophic Forgetting? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.00809 |