Beyond Size and Accuracy: The Impact of Model Compression on Fairness

Model compression is increasingly popular in the domain of deep learning. When addressing practical problems that use complex neural network models, the availability of computational resources can pose a significant challenge. While smaller models may provide more efficient solutions, they often com...

Full description

Saved in:
Bibliographic Details
Main Authors: Moumita Kamal, Douglas Talbert
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Online Access:https://journals.flvc.org/FLAIRS/article/view/135617
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154660740988928
author Moumita Kamal
Douglas Talbert
author_facet Moumita Kamal
Douglas Talbert
author_sort Moumita Kamal
collection DOAJ
description Model compression is increasingly popular in the domain of deep learning. When addressing practical problems that use complex neural network models, the availability of computational resources can pose a significant challenge. While smaller models may provide more efficient solutions, they often come at the cost of accuracy. To tackle this problem, researchers often use model compression techniques to transform large, complex models into simpler, faster models. These techniques aim to reduce the computational cost while minimizing the loss of accuracy. The majority of the model compression research focuses exclusively on model accuracy and size/speedup as performance metrics. This paper explores how different methods of model compression impact the fairness/bias of a model. We conducted our experiments using the COMPAS Recidivism Racial Bias dataset. We evaluated a variety of model compression techniques across multiple bias groups. Our findings indicate that the type and amount of compression have substantial impact on both the accuracy and fairness/bias of the model.
format Article
id doaj-art-d051e95d82a7482a89b31560b60c4032
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-d051e95d82a7482a89b31560b60c40322025-08-20T02:25:13ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13561771996Beyond Size and Accuracy: The Impact of Model Compression on FairnessMoumita Kamal0Douglas Talbert1https://orcid.org/0000-0001-8073-1134Tennessee Tech UniversityTennessee Tech UniversityModel compression is increasingly popular in the domain of deep learning. When addressing practical problems that use complex neural network models, the availability of computational resources can pose a significant challenge. While smaller models may provide more efficient solutions, they often come at the cost of accuracy. To tackle this problem, researchers often use model compression techniques to transform large, complex models into simpler, faster models. These techniques aim to reduce the computational cost while minimizing the loss of accuracy. The majority of the model compression research focuses exclusively on model accuracy and size/speedup as performance metrics. This paper explores how different methods of model compression impact the fairness/bias of a model. We conducted our experiments using the COMPAS Recidivism Racial Bias dataset. We evaluated a variety of model compression techniques across multiple bias groups. Our findings indicate that the type and amount of compression have substantial impact on both the accuracy and fairness/bias of the model.https://journals.flvc.org/FLAIRS/article/view/135617
spellingShingle Moumita Kamal
Douglas Talbert
Beyond Size and Accuracy: The Impact of Model Compression on Fairness
Proceedings of the International Florida Artificial Intelligence Research Society Conference
title Beyond Size and Accuracy: The Impact of Model Compression on Fairness
title_full Beyond Size and Accuracy: The Impact of Model Compression on Fairness
title_fullStr Beyond Size and Accuracy: The Impact of Model Compression on Fairness
title_full_unstemmed Beyond Size and Accuracy: The Impact of Model Compression on Fairness
title_short Beyond Size and Accuracy: The Impact of Model Compression on Fairness
title_sort beyond size and accuracy the impact of model compression on fairness
url https://journals.flvc.org/FLAIRS/article/view/135617
work_keys_str_mv AT moumitakamal beyondsizeandaccuracytheimpactofmodelcompressiononfairness
AT douglastalbert beyondsizeandaccuracytheimpactofmodelcompressiononfairness