Layer Pruning with Consensus: A Triple-Win Solution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mugnaini, Leandro Giusti, Duarte, Carolina Tavares, Costa, Anna H. Reali, Jordao, Artur
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912547685269504
author Mugnaini, Leandro Giusti
Duarte, Carolina Tavares
Costa, Anna H. Reali
Jordao, Artur
author_facet Mugnaini, Leandro Giusti
Duarte, Carolina Tavares
Costa, Anna H. Reali
Jordao, Artur
contents Layer pruning offers a promising alternative to standard structured pruning, effectively reducing computational costs, latency, and memory footprint. While notable layer-pruning approaches aim to detect unimportant layers for removal, they often rely on single criteria that may not fully capture the complex, underlying properties of layers. We propose a novel approach that combines multiple similarity metrics into a single expressive measure of low-importance layers, called the Consensus criterion. Our technique delivers a triple-win solution: low accuracy drop, high-performance improvement, and increased robustness to adversarial attacks. With up to 78.80% FLOPs reduction and performance on par with state-of-the-art methods across different benchmarks, our approach reduces energy consumption and carbon emissions by up to 66.99% and 68.75%, respectively. Additionally, it avoids shortcut learning and improves robustness by up to 4 percentage points under various adversarial attacks. Overall, the Consensus criterion demonstrates its effectiveness in creating robust, efficient, and environmentally friendly pruned models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Layer Pruning with Consensus: A Triple-Win Solution
Mugnaini, Leandro Giusti
Duarte, Carolina Tavares
Costa, Anna H. Reali
Jordao, Artur
Machine Learning
Computer Vision and Pattern Recognition
Layer pruning offers a promising alternative to standard structured pruning, effectively reducing computational costs, latency, and memory footprint. While notable layer-pruning approaches aim to detect unimportant layers for removal, they often rely on single criteria that may not fully capture the complex, underlying properties of layers. We propose a novel approach that combines multiple similarity metrics into a single expressive measure of low-importance layers, called the Consensus criterion. Our technique delivers a triple-win solution: low accuracy drop, high-performance improvement, and increased robustness to adversarial attacks. With up to 78.80% FLOPs reduction and performance on par with state-of-the-art methods across different benchmarks, our approach reduces energy consumption and carbon emissions by up to 66.99% and 68.75%, respectively. Additionally, it avoids shortcut learning and improves robustness by up to 4 percentage points under various adversarial attacks. Overall, the Consensus criterion demonstrates its effectiveness in creating robust, efficient, and environmentally friendly pruned models.
title Layer Pruning with Consensus: A Triple-Win Solution
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.14345