Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914208145211392 |
|---|---|
| author | Moussa, Hesham G. Hameed, Aroosa Akhavain, Arashmid |
| author_facet | Moussa, Hesham G. Hameed, Aroosa Akhavain, Arashmid |
| contents | To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop themselves adaptively. Catastrophic forgetting is a major challenge to the progress of Continual Learning approaches, where learning a new task usually results in a dramatic performance drop on previously learned ones. Many approaches have emerged to counteract the impact of CF. Most of the proposed approaches can be categorized into five classes: replay-based, regularization-based, optimization-based, representation-based, and architecture-based. In this work, we approach the problem from a different angle, specifically by considering the optimal sequencing of tasks as they are presented to the model. We investigate the role of task sequencing in mitigating CF and propose a method for determining the optimal task order. The proposed method leverages zero-shot scoring algorithms inspired by neural architecture search (NAS). Results demonstrate that intelligent task sequencing can substantially reduce CF. Moreover, when combined with traditional continual learning strategies, sequencing offers enhanced performance and robustness against forgetting. Additionally, the presented approaches can find applications in other fields, such as curriculum learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16871 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sequencing to Mitigate Catastrophic Forgetting in Continual Learning Moussa, Hesham G. Hameed, Aroosa Akhavain, Arashmid Machine Learning Artificial Intelligence To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop themselves adaptively. Catastrophic forgetting is a major challenge to the progress of Continual Learning approaches, where learning a new task usually results in a dramatic performance drop on previously learned ones. Many approaches have emerged to counteract the impact of CF. Most of the proposed approaches can be categorized into five classes: replay-based, regularization-based, optimization-based, representation-based, and architecture-based. In this work, we approach the problem from a different angle, specifically by considering the optimal sequencing of tasks as they are presented to the model. We investigate the role of task sequencing in mitigating CF and propose a method for determining the optimal task order. The proposed method leverages zero-shot scoring algorithms inspired by neural architecture search (NAS). Results demonstrate that intelligent task sequencing can substantially reduce CF. Moreover, when combined with traditional continual learning strategies, sequencing offers enhanced performance and robustness against forgetting. Additionally, the presented approaches can find applications in other fields, such as curriculum learning. |
| title | Sequencing to Mitigate Catastrophic Forgetting in Continual Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.16871 |