arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.13796cs.LGcs.AI
收藏

不要按下按钮!探索机器学习和迁移学习中的数据泄露风险

Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning

University of Naples Federico II(那不勒斯费德里科二世大学);University of Salerno(萨莱诺大学)

Andrea Apicella, Francesco Isgrò, Roberto Prevete

AI总结:

本文针对从业者因“按下按钮”式操作缺乏ML专业知识导致的问题,聚焦数据泄露风险,分类探讨其在ML工作流中的传播、与任务的联系及迁移学习中的表现,强调解决该问题对ML应用稳健性的重要性。

摘要:

机器学习(ML)已彻底改变了各个领域,在多个方面提供了预测能力。然而,随着ML工具的可及性日益提高,许多缺乏深厚ML专业知识的从业者采用“按下按钮”的方法,在没有充分理解底层算法的情况下使用用户友好的界面。虽然这种方法提供了便利,但它引发了对结果可靠性的担忧,导致了错误性能评估等挑战。本文探讨了ML中的一个关键问题,即数据泄露——非预期信息污染训练数据,影响模型性能评估。由于缺乏理解,用户可能会无意中忽略关键步骤,导致乐观的性能估计在现实场景中无法成立,评估性能与新数据实际性能之间的差异是一个重要问题。本文对ML中的数据泄露进行了分类,讨论了某些条件如何在ML工作流中传播,还探索了数据泄露与所处理特定任务的联系,研究了其在迁移学习中的发生情况,并比较了标准归纳ML与转导ML框架。结论总结了关键发现,强调解决数据泄露对构建稳健可靠的ML应用的重要性。

英文摘要:

Machine Learning (ML) has revolutionized various domains, offering predictive capabilities in several areas. However, with the increasing accessibility of ML tools, many practitioners, lacking deep ML expertise, adopt a "push the button" approach, utilizing user-friendly interfaces without a thorough understanding of underlying algorithms. While this approach provides convenience, it raises concerns about the reliability of outcomes, leading to challenges such as incorrect performance evaluation. This paper addresses a critical issue in ML, known as data leakage, where unintended information contaminates the training data, impacting model performance evaluation. Users, due to a lack of understanding, may inadvertently overlook crucial steps, leading to optimistic performance estimates that may not hold in real-world scenarios. The discrepancy between evaluated and actual performance on new data is a significant concern. In particular, this paper categorizes data leakage in ML, discussing how certain conditions can propagate through the ML workflow. Furthermore, it explores the connection between data leakage and the specific task being addressed, investigates its occurrence in Transfer Learning, and compares standard inductive ML with transductive ML frameworks. The conclusion summarizes key findings, emphasizing the importance of addressing data leakage for robust and reliable ML applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑