Make Continual Learning Stronger via C-Flat
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912098942976000 |
|---|---|
| author | Bian, Ang Li, Wei Yuan, Hangjie Yu, Chengrong Wang, Mang Zhao, Zixiang Lu, Aojun Ji, Pengliang Feng, Tao |
| author_facet | Bian, Ang Li, Wei Yuan, Hangjie Yu, Chengrong Wang, Mang Zhao, Zixiang Lu, Aojun Ji, Pengliang Feng, Tao |
| contents | Model generalization ability upon incrementally acquiring dynamically updating knowledge from sequentially arriving tasks is crucial to tackle the sensitivity-stability dilemma in Continual Learning (CL). Weight loss landscape sharpness minimization seeking for flat minima lying in neighborhoods with uniform low loss or smooth gradient is proven to be a strong training regime improving model generalization compared with loss minimization based optimizer like SGD. Yet only a few works have discussed this training regime for CL, proving that dedicated designed zeroth-order sharpness optimizer can improve CL performance. In this work, we propose a Continual Flatness (C-Flat) method featuring a flatter loss landscape tailored for CL. C-Flat could be easily called with only one line of code and is plug-and-play to any CL methods. A general framework of C-Flat applied to all CL categories and a thorough comparison with loss minima optimizer and flat minima based CL approaches is presented in this paper, showing that our method can boost CL performance in almost all cases. Code is available at https://github.com/WanNaa/C-Flat. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00986 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Make Continual Learning Stronger via C-Flat Bian, Ang Li, Wei Yuan, Hangjie Yu, Chengrong Wang, Mang Zhao, Zixiang Lu, Aojun Ji, Pengliang Feng, Tao Machine Learning Computer Vision and Pattern Recognition Model generalization ability upon incrementally acquiring dynamically updating knowledge from sequentially arriving tasks is crucial to tackle the sensitivity-stability dilemma in Continual Learning (CL). Weight loss landscape sharpness minimization seeking for flat minima lying in neighborhoods with uniform low loss or smooth gradient is proven to be a strong training regime improving model generalization compared with loss minimization based optimizer like SGD. Yet only a few works have discussed this training regime for CL, proving that dedicated designed zeroth-order sharpness optimizer can improve CL performance. In this work, we propose a Continual Flatness (C-Flat) method featuring a flatter loss landscape tailored for CL. C-Flat could be easily called with only one line of code and is plug-and-play to any CL methods. A general framework of C-Flat applied to all CL categories and a thorough comparison with loss minima optimizer and flat minima based CL approaches is presented in this paper, showing that our method can boost CL performance in almost all cases. Code is available at https://github.com/WanNaa/C-Flat. |
| title | Make Continual Learning Stronger via C-Flat |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.00986 |