Saved in:
Bibliographic Details
Main Authors: Guo, Yuxiang, Gao, Xiaopeng, Jiang, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929281057161216
author Guo, Yuxiang
Gao, Xiaopeng
Jiang, Bo
author_facet Guo, Yuxiang
Gao, Xiaopeng
Jiang, Bo
contents Previous works on Just-In-Time (JIT) defect prediction tasks have primarily applied pre-trained models directly, neglecting the configurations of their fine-tuning process. In this study, we perform a systematic empirical study to understand the impact of the settings of the fine-tuning process on BERT-style pre-trained model for JIT defect prediction. Specifically, we explore the impact of different parameter freezing settings, parameter initialization settings, and optimizer strategies on the performance of BERT-style models for JIT defect prediction. Our findings reveal the crucial role of the first encoder layer in the BERT-style model and the project sensitivity to parameter initialization settings. Another notable finding is that the addition of a weight decay strategy in the Adam optimizer can slightly improve model performance. Additionally, we compare performance using different feature extractors (FCN, CNN, LSTM, transformer) and find that a simple network can achieve great performance. These results offer new insights for fine-tuning pre-trained models for JIT defect prediction. We combine these findings to find a cost-effective fine-tuning method based on LoRA, which achieve a comparable performance with only one-third memory consumption than original fine-tuning process.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11158
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Empirical Study on JIT Defect Prediction Based on BERT-style Model
Guo, Yuxiang
Gao, Xiaopeng
Jiang, Bo
Software Engineering
Previous works on Just-In-Time (JIT) defect prediction tasks have primarily applied pre-trained models directly, neglecting the configurations of their fine-tuning process. In this study, we perform a systematic empirical study to understand the impact of the settings of the fine-tuning process on BERT-style pre-trained model for JIT defect prediction. Specifically, we explore the impact of different parameter freezing settings, parameter initialization settings, and optimizer strategies on the performance of BERT-style models for JIT defect prediction. Our findings reveal the crucial role of the first encoder layer in the BERT-style model and the project sensitivity to parameter initialization settings. Another notable finding is that the addition of a weight decay strategy in the Adam optimizer can slightly improve model performance. Additionally, we compare performance using different feature extractors (FCN, CNN, LSTM, transformer) and find that a simple network can achieve great performance. These results offer new insights for fine-tuning pre-trained models for JIT defect prediction. We combine these findings to find a cost-effective fine-tuning method based on LoRA, which achieve a comparable performance with only one-third memory consumption than original fine-tuning process.
title An Empirical Study on JIT Defect Prediction Based on BERT-style Model
topic Software Engineering
url https://arxiv.org/abs/2403.11158