paper-with-me

Papers

Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach

2021-11-01 · Qisheng He, Weisong Shi, Ming Dong

As a deep learning model typically contains millions of trainable weights, there has been a growing demand for a more efficient network structure with reduced storage space and improved run-time efficiency. Pruning is one of the most popular network compression techniques. In this paper, we propose a novel unstructured pruning pipeline, Attention-based Simultaneous sparse structure and Weight Learning (ASWL). Unlike traditional channel-wise or weight-wise attention mechanism, ASWL proposed an efficient algorithm to calculate the pruning ratio through layer-wise attention for each layer, and both weights for the dense network and the sparse network are tracked so that the pruned structure is simultaneously learned from randomly initialized weights. Our experiments on MNIST, Cifar10, and ImageNet show that ASWL achieves superior pruning results in terms of accuracy, pruning ratio and operating efficiency when compared with state-of-the-art network pruning methods.

📄 PDF Abstract BibTeX arXiv:2111.02399

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Pruning from Scratch

2019-09-27 · Yulong Wang, Xiaolu Zhang, Lingxi Xie, Jun Zhou 외

Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large and redundant network, and then determi…

Network Pruning

Pruning by Active Attention Manipulation

2022-10-20 · Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus 외

Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-scoring concept named pruning by active att…

Rethinking the Value of Network Pruning

2018-10-11 · ICLR 2019 5 · Zhuang Liu, Ming-Jie Sun, Tinghui Zhou, Gao Huang 외

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning…

Network PruningNeural Architecture Search

Magnificent Minified Models

2023-06-16 · Rich Harang, Hillary Sanders

This paper concerns itself with the task of taking a large trained neural network and 'compressing' it to be smaller by deleting parameters or entire neurons, with minimal decreases in the resulting model accuracy. We co…

Quantization

A Closer Look at Structured Pruning for Neural Network Compression

2018-10-10 · Elliot J. Crowley, Jack Turner, Amos Storkey, Michael O'Boyle

Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network. Howe…

Network PruningNeural Network Compression