The reviewed record of science sign in
Pith

arxiv: 2111.02399 · v2 · pith:JVLUKMPD · submitted 2021-11-01 · cs.LG · cs.CV

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JVLUKMPDrecord.jsonopen to challenge →

classification cs.LG cs.CV
keywords pruningnetworkstructureweightsaswlattentionlearningefficiency
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.