Continual Learning with Weight Interpolation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916198236553216 |
|---|---|
| author | Kozal, Jędrzej Wasilewski, Jan Krawczyk, Bartosz Woźniak, Michał |
| author_facet | Kozal, Jędrzej Wasilewski, Jan Krawczyk, Bartosz Woźniak, Michał |
| contents | Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, effectively merging two models to facilitate exploration of local minima emerging after arrival of new concepts. Moreover, we demonstrate that our approach can complement existing rehearsal-based replay approaches, improving their accuracy and further mitigating the forgetting phenomenon. Additionally, our method provides an intuitive mechanism for controlling the stability-plasticity trade-off. Experimental results showcase the significant performance enhancement to state-of-the-art experience replay algorithms the proposed weight consolidation approach offers. Our algorithm can be downloaded from https://github.com/jedrzejkozal/weight-interpolation-cl. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04002 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Continual Learning with Weight Interpolation Kozal, Jędrzej Wasilewski, Jan Krawczyk, Bartosz Woźniak, Michał Machine Learning Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, effectively merging two models to facilitate exploration of local minima emerging after arrival of new concepts. Moreover, we demonstrate that our approach can complement existing rehearsal-based replay approaches, improving their accuracy and further mitigating the forgetting phenomenon. Additionally, our method provides an intuitive mechanism for controlling the stability-plasticity trade-off. Experimental results showcase the significant performance enhancement to state-of-the-art experience replay algorithms the proposed weight consolidation approach offers. Our algorithm can be downloaded from https://github.com/jedrzejkozal/weight-interpolation-cl. |
| title | Continual Learning with Weight Interpolation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.04002 |