Deriva-ML：一种实现可复现机器学习模型的持续 FAIR 化方法
Deriva-ML: A Continuous FAIRness Approach to Reproducible Machine Learning Models
AI总结：
本文提出 Deriva-ML，通过贯穿 ML 研究全生命周期的 FAIR 数据管理工具与最佳实践，提升 eScience 团队构建正确、可复现机器学习解决方案的能力。
摘要：
人工智能（AI）和机器学习（ML）正越来越多地用于 eScience 应用[9]。尽管这些方法具有巨大潜力，但已有文献表明，由于训练和验证模型所用数据管理不当或误用，基于 ML 的方法经常产生不正确或不可复现的结果[12,15]。人们认识到高质量数据对于获得正确 ML 结果的必要性，由此催生了以数据为中心的 ML 方法，将核心重点从模型开发转向创建高质量数据集，以训练和验证模型[14,20]。然而，目前可供以数据为中心的方法用于探索和评估 eScience 问题 ML 解决方案的工具和方法仍然有限；这类问题通常需要协作式多学科团队处理模型和数据，而随着研究展开，这些模型和数据会快速演化[1]。本文展示了基于以下原则的数据管理工具如何显著改善 ML 应用所用数据的质量：ML 的所有数据都应是可发现、可访问、可互操作和可重用的（即 FAIR[26]）。当这些工具与将其应用于基于 ML 的 eScience 研究整个生命周期的最佳实践相结合时，我们能够显著提升 eScience 团队创建正确且可复现 ML 解决方案的能力。我们提出了此类工具的架构和实现，并通过两个用例演示如何使用它们来改进基于 ML 的 eScience 研究。
英文摘要：
Increasingly, artificial intelligence (AI) and machine learning (ML) are used in eScience applications [9]. While these approaches have great potential, the literature has shown that ML-based approaches frequently suffer from results that are either incorrect or unreproducible due to mismanagement or misuse of data used for training and validating the models [12, 15]. Recognition of the necessity of high-quality data for correct ML results has led to data-centric ML approaches that shift the central focus from model development to creation of high-quality data sets to train and validate the models [14, 20]. However, there are limited tools and methods available for data-centric approaches to explore and evaluate ML solutions for eScience problems which often require collaborative multidisciplinary teams working with models and data that will rapidly evolve as an investigation unfolds [1]. In this paper, we show how data management tools based on the principle that all of the data for ML should be findable, accessible, interoperable and reusable (i.e. FAIR [26]) can significantly improve the quality of data that is used for ML applications. When combined with best practices that apply these tools to the entire life cycle of an ML-based eScience investigation, we can significantly improve the ability of an eScience team to create correct and reproducible ML solutions. We propose an architecture and implementation of such tools and demonstrate through two use cases how they can be used to improve ML-based eScience investigations.
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。
