Mutual Information Preserving Neural Network Pruning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Westphal, Charles, Hailes, Stephen, Musolesi, Mirco
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916594543755264
author Westphal, Charles
Hailes, Stephen
Musolesi, Mirco
author_facet Westphal, Charles
Hailes, Stephen
Musolesi, Mirco
contents Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers have focused either on pruning at initialization or after training. However, recent theoretical findings have shown that the sample efficiency of robust pruned models is proportional to the mutual information (MI) between the pruning masks and the model's training datasets, \textit{whether at initialization or after training}. In this paper, starting from these results, we introduce Mutual Information Preserving Pruning (MIPP), a structured activation-based pruning technique applicable before or after training. The core principle of MIPP is to select nodes in a way that conserves MI shared between the activations of adjacent layers, and consequently between the data and masks. Approaching the pruning problem in this manner means we can prove that there exists a function that can map the pruned upstream layer's activations to the downstream layer's, implying re-trainability. We demonstrate that MIPP consistently outperforms state-of-the-art methods, regardless of whether pruning is performed before or after training.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00147
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mutual Information Preserving Neural Network Pruning
Westphal, Charles
Hailes, Stephen
Musolesi, Mirco
Machine Learning
Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers have focused either on pruning at initialization or after training. However, recent theoretical findings have shown that the sample efficiency of robust pruned models is proportional to the mutual information (MI) between the pruning masks and the model's training datasets, \textit{whether at initialization or after training}. In this paper, starting from these results, we introduce Mutual Information Preserving Pruning (MIPP), a structured activation-based pruning technique applicable before or after training. The core principle of MIPP is to select nodes in a way that conserves MI shared between the activations of adjacent layers, and consequently between the data and masks. Approaching the pruning problem in this manner means we can prove that there exists a function that can map the pruned upstream layer's activations to the downstream layer's, implying re-trainability. We demonstrate that MIPP consistently outperforms state-of-the-art methods, regardless of whether pruning is performed before or after training.
title Mutual Information Preserving Neural Network Pruning
topic Machine Learning
url https://arxiv.org/abs/2411.00147