Combining Relevance and Magnitude for Resource-Aware DNN Pruning
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_ | 1866910895613935616 |
|---|---|
| author | Chiasserini, Carla Fabiana Malandrino, Francesco Molner, Nuria Zhao, Zhiqiang |
| author_facet | Chiasserini, Carla Fabiana Malandrino, Francesco Molner, Nuria Zhao, Zhiqiang |
| contents | Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios. In this context, the pruning technique, i.e., how to choose the parameters to remove, is critical to the system performance. In this paper, we propose a novel pruning approach, called FlexRel and predicated upon combining training-time and inference-time information, namely, parameter magnitude and relevance, in order to improve the resulting accuracy whilst saving both computational resources and bandwidth. Our performance evaluation shows that FlexRel is able to achieve higher pruning factors, saving over 35% bandwidth for typical accuracy targets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13088 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Combining Relevance and Magnitude for Resource-Aware DNN Pruning Chiasserini, Carla Fabiana Malandrino, Francesco Molner, Nuria Zhao, Zhiqiang Machine Learning Neural and Evolutionary Computing Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios. In this context, the pruning technique, i.e., how to choose the parameters to remove, is critical to the system performance. In this paper, we propose a novel pruning approach, called FlexRel and predicated upon combining training-time and inference-time information, namely, parameter magnitude and relevance, in order to improve the resulting accuracy whilst saving both computational resources and bandwidth. Our performance evaluation shows that FlexRel is able to achieve higher pruning factors, saving over 35% bandwidth for typical accuracy targets. |
| title | Combining Relevance and Magnitude for Resource-Aware DNN Pruning |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2405.13088 |