{"title":"本地通用规则解释器（LUX）","authors":"Szymon Bobek, Grzegorz J. Nalepa","doi":"10.1016/j.softx.2025.102102","DOIUrl":null,"url":null,"abstract":"<div><div>LUX (Local Universal Rule-Based Explainer) is an explainable artificial intelligence (XAI) method that produces explanations for any type of machine-learning model designed particularly for the tabular data. It generates local explanations and counterfactual explanations in a form of human-readable, visual, and executable rules. The main advantage of LUX over other solutions is that it uses a shared model to generate explanations and minimizes the usage of synthetic data with the novel SHAP-guided sampling method. This allows obtaining explanations that are representative, plausible and consistent. The software implementation was released as an open-source Python package under the MIT License. It is compliant with the scikit-learn API interface, allowing for seamless integration with machine learning pipelines.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"30 ","pages":"Article 102102"},"PeriodicalIF":1.9000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Local Universal Rule-based eXplainer (LUX)\",\"authors\":\"Szymon Bobek, Grzegorz J. Nalepa\",\"doi\":\"10.1016/j.softx.2025.102102\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>LUX (Local Universal Rule-Based Explainer) is an explainable artificial intelligence (XAI) method that produces explanations for any type of machine-learning model designed particularly for the tabular data. It generates local explanations and counterfactual explanations in a form of human-readable, visual, and executable rules. The main advantage of LUX over other solutions is that it uses a shared model to generate explanations and minimizes the usage of synthetic data with the novel SHAP-guided sampling method. This allows obtaining explanations that are representative, plausible and consistent. The software implementation was released as an open-source Python package under the MIT License. It is compliant with the scikit-learn API interface, allowing for seamless integration with machine learning pipelines.</div></div>\",\"PeriodicalId\":21905,\"journal\":{\"name\":\"SoftwareX\",\"volume\":\"30 \",\"pages\":\"Article 102102\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SoftwareX\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S235271102500069X\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/2/27 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SoftwareX","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S235271102500069X","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/27 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
LUX (Local Universal Rule-Based Explainer) is an explainable artificial intelligence (XAI) method that produces explanations for any type of machine-learning model designed particularly for the tabular data. It generates local explanations and counterfactual explanations in a form of human-readable, visual, and executable rules. The main advantage of LUX over other solutions is that it uses a shared model to generate explanations and minimizes the usage of synthetic data with the novel SHAP-guided sampling method. This allows obtaining explanations that are representative, plausible and consistent. The software implementation was released as an open-source Python package under the MIT License. It is compliant with the scikit-learn API interface, allowing for seamless integration with machine learning pipelines.
期刊介绍：
SoftwareX aims to acknowledge the impact of software on today''s research practice, and on new scientific discoveries in almost all research domains. SoftwareX also aims to stress the importance of the software developers who are, in part, responsible for this impact. To this end, SoftwareX aims to support publication of research software in such a way that: The software is given a stamp of scientific relevance, and provided with a peer-reviewed recognition of scientific impact; The software developers are given the credits they deserve; The software is citable, allowing traditional metrics of scientific excellence to apply; The academic career paths of software developers are supported rather than hindered; The software is publicly available for inspection, validation, and re-use. Above all, SoftwareX aims to inform researchers about software applications, tools and libraries with a (proven) potential to impact the process of scientific discovery in various domains. The journal is multidisciplinary and accepts submissions from within and across subject domains such as those represented within the broad thematic areas below: Mathematical and Physical Sciences; Environmental Sciences; Medical and Biological Sciences; Humanities, Arts and Social Sciences. Originating from these broad thematic areas, the journal also welcomes submissions of software that works in cross cutting thematic areas, such as citizen science, cybersecurity, digital economy, energy, global resource stewardship, health and wellbeing, etcetera. SoftwareX specifically aims to accept submissions representing domain-independent software that may impact more than one research domain.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
