Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: You, Hanmo, Wang, Zan, Dong, Zishuo, Mo, Luanqi, Zhao, Jianjun, Chen, Junjie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.23745
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911344590061568
author You, Hanmo
Wang, Zan
Dong, Zishuo
Mo, Luanqi
Zhao, Jianjun
Chen, Junjie
author_facet You, Hanmo
Wang, Zan
Dong, Zishuo
Mo, Luanqi
Zhao, Jianjun
Chen, Junjie
contents Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empirical study on 16 state-of-the-art DL model fixing approaches, spanning model-level, layer-level, and neuron-level categories, to comprehensively evaluate their performance. We assess not only their fixing effectiveness (their primary purpose) but also their impact on other critical properties, such as robustness, fairness, and backward compatibility. To ensure comprehensive and fair evaluation, we employ a diverse set of datasets, model architectures, and application domains within a uniform experimental setup for experimentation. We summarize several key findings with implications for both industry and academia. For example, model-level approaches demonstrate superior fixing effectiveness compared to others. No single approach can achieve the best fixing performance while improving accuracy and maintaining all other properties. Thus, academia should prioritize research on mitigating these side effects. These insights highlight promising directions for future exploration in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23745
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Comprehensive Study of Deep Learning Model Fixing Approaches
You, Hanmo
Wang, Zan
Dong, Zishuo
Mo, Luanqi
Zhao, Jianjun
Chen, Junjie
Machine Learning
Software Engineering
Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empirical study on 16 state-of-the-art DL model fixing approaches, spanning model-level, layer-level, and neuron-level categories, to comprehensively evaluate their performance. We assess not only their fixing effectiveness (their primary purpose) but also their impact on other critical properties, such as robustness, fairness, and backward compatibility. To ensure comprehensive and fair evaluation, we employ a diverse set of datasets, model architectures, and application domains within a uniform experimental setup for experimentation. We summarize several key findings with implications for both industry and academia. For example, model-level approaches demonstrate superior fixing effectiveness compared to others. No single approach can achieve the best fixing performance while improving accuracy and maintaining all other properties. Thus, academia should prioritize research on mitigating these side effects. These insights highlight promising directions for future exploration in this field.
title A Comprehensive Study of Deep Learning Model Fixing Approaches
topic Machine Learning
Software Engineering
url https://arxiv.org/abs/2512.23745