LaF: Labeling-free model selection for automated deep neural network reusing
pplying deep learning (DL) to science is a new trend in recent years, which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build DL models, all of them are complex and costly. Therefor...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8476 https://ink.library.smu.edu.sg/context/sis_research/article/9479/viewcontent/LaF__Labeling_free_Model_Selection_for_Automated_Deep_Neural_Network_Reusing.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9479 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-94792024-01-04T09:12:24Z LaF: Labeling-free model selection for automated deep neural network reusing HU, Qiang GUO, Yuejun XIE, Xiaofei CORDY, Maxime PAPADAKIS, Mike TRAON, Yves Le pplying deep learning (DL) to science is a new trend in recent years, which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build DL models, all of them are complex and costly. Therefore, reusing the open-sourced pre-trained model is a practical way to bypass this hurdle for developers. Given a specific task, developers can collect massive pre-trained deep neural networks from public sources for reusing. However, testing the performance (e.g., accuracy and robustness) of multiple deep neural networks (DNNs) and recommending which model should be used is challenging regarding the scarcity of labeled data and the demand for domain expertise. In this article, we propose a labeling-free (LaF) model selection approach to overcome the limitations of labeling efforts for automated model reusing. The main idea is to statistically learn a Bayesian model to infer the models’ specialty only based on predicted labels. We evaluate LaF using nine benchmark datasets, including image, text, and source code, and 165 DNNs, considering both the accuracy and robustness of models. The experimental results demonstrate that LaF outperforms the baseline methods by up to 0.74 and 0.53 on Spearman’s correlation and Kendall’s τ, respectively. 2023-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8476 info:doi/10.1145/3611666 https://ink.library.smu.edu.sg/context/sis_research/article/9479/viewcontent/LaF__Labeling_free_Model_Selection_for_Automated_Deep_Neural_Network_Reusing.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computing methodologies Artificial intelligence Software and its engineering Software creation and management Software development process management Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Computing methodologies Artificial intelligence Software and its engineering Software creation and management Software development process management Databases and Information Systems |
spellingShingle |
Computing methodologies Artificial intelligence Software and its engineering Software creation and management Software development process management Databases and Information Systems HU, Qiang GUO, Yuejun XIE, Xiaofei CORDY, Maxime PAPADAKIS, Mike TRAON, Yves Le LaF: Labeling-free model selection for automated deep neural network reusing |
description |
pplying deep learning (DL) to science is a new trend in recent years, which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build DL models, all of them are complex and costly. Therefore, reusing the open-sourced pre-trained model is a practical way to bypass this hurdle for developers. Given a specific task, developers can collect massive pre-trained deep neural networks from public sources for reusing. However, testing the performance (e.g., accuracy and robustness) of multiple deep neural networks (DNNs) and recommending which model should be used is challenging regarding the scarcity of labeled data and the demand for domain expertise. In this article, we propose a labeling-free (LaF) model selection approach to overcome the limitations of labeling efforts for automated model reusing. The main idea is to statistically learn a Bayesian model to infer the models’ specialty only based on predicted labels. We evaluate LaF using nine benchmark datasets, including image, text, and source code, and 165 DNNs, considering both the accuracy and robustness of models. The experimental results demonstrate that LaF outperforms the baseline methods by up to 0.74 and 0.53 on Spearman’s correlation and Kendall’s τ, respectively. |
format |
text |
author |
HU, Qiang GUO, Yuejun XIE, Xiaofei CORDY, Maxime PAPADAKIS, Mike TRAON, Yves Le |
author_facet |
HU, Qiang GUO, Yuejun XIE, Xiaofei CORDY, Maxime PAPADAKIS, Mike TRAON, Yves Le |
author_sort |
HU, Qiang |
title |
LaF: Labeling-free model selection for automated deep neural network reusing |
title_short |
LaF: Labeling-free model selection for automated deep neural network reusing |
title_full |
LaF: Labeling-free model selection for automated deep neural network reusing |
title_fullStr |
LaF: Labeling-free model selection for automated deep neural network reusing |
title_full_unstemmed |
LaF: Labeling-free model selection for automated deep neural network reusing |
title_sort |
laf: labeling-free model selection for automated deep neural network reusing |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8476 https://ink.library.smu.edu.sg/context/sis_research/article/9479/viewcontent/LaF__Labeling_free_Model_Selection_for_Automated_Deep_Neural_Network_Reusing.pdf |
_version_ |
1787590776555831296 |