Sequence Transferability and Task Order Selection 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_ | 1866910820292624384 |
|---|---|
| author | Nguyen, Thinh Nguyen, Cuong N. Pham, Quang Nguyen, Binh T. Ramasamy, Savitha Li, Xiaoli Nguyen, Cuong V. |
| author_facet | Nguyen, Thinh Nguyen, Cuong N. Pham, Quang Nguyen, Binh T. Ramasamy, Savitha Li, Xiaoli Nguyen, Cuong V. |
| contents | In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain underdeveloped despite encouraging progress in methodology development. In this work, we investigate the impacts of sequence transferability on continual learning and propose two novel measures that capture the total transferability of a task sequence, either in the forward or backward direction. Based on the empirical properties of these measures, we then develop a new method for the task order selection problem in continual learning. Our method can be shown to offer a better performance than the conventional strategy of random task selection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06544 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sequence Transferability and Task Order Selection in Continual Learning Nguyen, Thinh Nguyen, Cuong N. Pham, Quang Nguyen, Binh T. Ramasamy, Savitha Li, Xiaoli Nguyen, Cuong V. Machine Learning Computer Vision and Pattern Recognition 68T45, 68T01 In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain underdeveloped despite encouraging progress in methodology development. In this work, we investigate the impacts of sequence transferability on continual learning and propose two novel measures that capture the total transferability of a task sequence, either in the forward or backward direction. Based on the empirical properties of these measures, we then develop a new method for the task order selection problem in continual learning. Our method can be shown to offer a better performance than the conventional strategy of random task selection. |
| title | Sequence Transferability and Task Order Selection in Continual Learning |
| topic | Machine Learning Computer Vision and Pattern Recognition 68T45, 68T01 |
| url | https://arxiv.org/abs/2502.06544 |