Shapley Pruning for Neural Network Compression
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_ | 1866916332619956224 |
|---|---|
| author | Adamczewski, Kamil Li, Yawei van Gool, Luc |
| author_facet | Adamczewski, Kamil Li, Yawei van Gool, Luc |
| contents | Neural network pruning is a rich field with a variety of approaches. In this work, we propose to connect the existing pruning concepts such as leave-one-out pruning and oracle pruning and develop them into a more general Shapley value-based framework that targets the compression of convolutional neural networks. To allow for practical applications in utilizing the Shapley value, this work presents the Shapley value approximations, and performs the comparative analysis in terms of cost-benefit utility for the neural network compression. The proposed ranks are evaluated against a new benchmark, Oracle rank, constructed based on oracle sets. The broad experiments show that the proposed normative ranking and its approximations show practical results, obtaining state-of-the-art network compression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15875 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Shapley Pruning for Neural Network Compression Adamczewski, Kamil Li, Yawei van Gool, Luc Machine Learning Computer Vision and Pattern Recognition Neural network pruning is a rich field with a variety of approaches. In this work, we propose to connect the existing pruning concepts such as leave-one-out pruning and oracle pruning and develop them into a more general Shapley value-based framework that targets the compression of convolutional neural networks. To allow for practical applications in utilizing the Shapley value, this work presents the Shapley value approximations, and performs the comparative analysis in terms of cost-benefit utility for the neural network compression. The proposed ranks are evaluated against a new benchmark, Oracle rank, constructed based on oracle sets. The broad experiments show that the proposed normative ranking and its approximations show practical results, obtaining state-of-the-art network compression. |
| title | Shapley Pruning for Neural Network Compression |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.15875 |