一句话：提出用联邦学习在保护隐私前提下利用非开源项目数据训练软件工程AI模型，并初步验证其可行性。
软件工程研究长期依赖 GitHub 等平台的开源项目制品，而非开源项目因数据隐私问题难以被利用，导致相关 AI 模型训练数据受限。本文提出用联邦学习在保护隐私的前提下利用非开源数据训练软件工程 AI 模型，从而促进工业界与研究者合作。作者以已有研究中标注 bug 修复提交的分类器为案例进行初步评估：联邦方法取得 0.83 的 F1 值，集中式方法为 0.84，表明该方案可行。最后讨论了联邦学习在软件工程研究中的潜在影响与愿景。
The availability of open source projects on platforms like GitHub has led to the wide use of the artifacts from these projects in software engineering research. These publicly available artifacts have been used to train artificial intelligence models used in various empirical studies and the development of tools. However, these advancements have missed out on the artifacts from non-open source projects due to the unavailability of the data. A major cause for the unavailability of the data from non-open source repositories is the issue concerning data privacy. In this paper, we propose using federated learning to address the issue of data privacy to enable the use of data from non-open source to train AI models used in software engineering research. We believe that this can potentially enable industries to collaborate with software engineering researchers without concerns about privacy. We present the preliminary evaluation of the use of federated learning to train a classifier to label bug-fix commits from an existing study to demonstrate its feasibility. The federated approach achieved an F1 score of 0.83 compared to a score of 0.84 using the centralized approach. We also present our vision of the potential implications of the use of federated learning in software engineering research.
DOI 原文 ·
@inproceedings{paperbot7036,
title = {Exploring the under-explored terrain of non-open source data for software engineering through the lens of federated learning},
author = {Shriram Shanbhag and Sridhar Chimalakonda},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3560883}
}