SUBP: Soft Uniform Block Pruning for 1×N Sparse CNNs Multithreading Acceleration

Jun Chen, Yong Liu, Jingyang Xiang, Siqi Li, Shipeng Bai, Yukai Ma, Guang Dai

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• JingyangXiang/SUBP — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The study of sparsity in Convolutional Neural Networks (CNNs) has become widespread to compress and accelerate models in environments with limited resources. By constraining N consecutive weights along the output channel to be group-wise non-zero, the recent network with 1×N sparsity has received tremendous popularity for its three outstanding advantages: 1) A large amount of storage space saving by a Block Sparse Row matrix. 2) Excellent performance at a high sparsity. 3) Significant speedups on CPUs with Advanced Vector Extensions. Recent work requires selecting and fine-tuning 1×N sparse weights based on dense pre-trained weights, leading to the problems such as expensive training cost and memory access, sub-optimal model quality, as well as unbalanced workload across threads (different sparsity across output channels). To overcome them, this paper proposes a novel Soft Uniform Block Pruning (SUBP) approach to train a uniform 1×N sparse structured network from scratch. Specifically, our approach tends to repeatedly allow pruned blocks to regrow to the network based on block angular redundancy and importance sampling in a uniform manner throughout the training process. It not only makes the model less dependent on pre-training, reduces the model redundancy and the risk of pruning the important blocks permanently but also achieves balanced workload. Empirically, on ImageNet, comprehensive experiments across various CNN architectures show that our SUBP consistently outperforms existing 1×N and structured sparsity methods based on pre-trained models or training from scratch. Source codes and models are available at https://github.com/JingyangXiang/SUBP.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.06218")
get_code_for_paper("2310.06218")
have("2310.06218")

Connect an agent — have() is free.