# Magnitude Attention-based Dynamic Pruning

Source: [Magnitude Attention-based Dynamic Pruning](<https://www.sota2.com/research/paper/68fa6f9f1e209131cea46afe>)

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

Data updated: 2025-10-26T01:24:25.039Z

Authors: Jihye Back, Namhyuk Ahn, Jangho Kim

Published: 2023-06-08T09:20:51.000Z

## Abstract

Existing pruning methods utilize the importance of each weight based on specified criteria only when searching for a sparse structure but do not utilize it during training. In this work, we propose a novel approach - \\textbf{M}agnitude \\textbf{A}ttention-based Dynamic \\textbf{P}runing (MAP) method, which applies the importance of weights throughout both the forward and backward paths to explore sparse model structures dynamically. Magnitude attention is defined based on the magnitude of weights as continuous real-valued numbers enabling a seamless transition from a redundant to an effective sparse network by promoting efficient exploration. Additionally, the attention mechanism ensures more effective updates for important layers within the sparse network. In later stages of training, our approach shifts from exploration to exploitation, exclusively updating the sparse model composed of crucial weights based on the explored structure, resulting in pruned models that not only achieve performance comparable to dense models but also outperform previous pruning methods on CIFAR-10/100 and ImageNet.

## 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/2306.05056>)

[PDF](<https://arxiv.org/pdf/2306.05056.pdf>)