# Dual sparse training framework: inducing activation map sparsity via Transformed $\\ell1$ regularization

Source: [Dual sparse training framework: inducing activation map sparsity via Transformed $\\ell1$ regularization](<https://www.sota2.com/research/paper/68fa73601e209131cea5bff8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:34:03.698Z

Authors: Xiaolong Yu, Cong Tian

Published: 2024-05-30T03:11:21.000Z

## Abstract

Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational and storage limitations. To address this issue, researchers have proposed techniques such as model compression, activation sparsity induction, and hardware accelerators. This paper presents a method to induce the sparsity of activation maps based on Transformed $\\ell1$ regularization, so as to improve the research in the field of activation sparsity induction. Further, the method is innovatively combined with traditional pruning, constituting a dual sparse training framework. Compared to previous methods, Transformed $\\ell1$ can achieve higher sparsity and better adapt to different network structures. Experimental results show that the method achieves improvements by more than 20\\% in activation map sparsity on most models and corresponding datasets without compromising the accuracy. Specifically, it achieves a 27.52\\% improvement for ResNet18 on the ImageNet dataset, and a 44.04\\% improvement for LeNet5 on the MNIST dataset. In addition, the dual sparse training framework can greatly reduce the computational load and provide potential for reducing the required storage during runtime. Specifically, the ResNet18 and ResNet50 models obtained by the dual sparse training framework respectively reduce 81.7\\% and 84.13\\% of multiplicative floating-point operations, while maintaining accuracy and a low pruning rate.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.19652>)

[PDF](<https://arxiv.org/pdf/2405.19652.pdf>)
