arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04665cs.LG
收藏

IIFE:基于交互信息的自动化特征工程

IIFE: Interaction Information Based Automated Feature Engineering

Northwestern University(西北大学);Allstate Insurance Company(好事达保险公司)

Tom Overman, Diego Klabjan, Jean Utke

AI总结:

本文提出基于交互信息的自动化特征工程算法IIFE,通过信息论视角识别协同特征对,提升预测性能,并改进现有AutoFE算法,同时揭示实验设置问题。

摘要:

自动化特征工程(AutoFE)是自动构建和选择有助于提升下游预测性能的新特征的过程。传统特征工程需要大量的领域知识和耗时的迭代测试,而AutoFE致力于使特征工程对所有数据科学从业者变得简单易用。我们提出了一种新的AutoFE算法IIFE,该算法基于通过称为交互信息的信息论视角来确定哪些特征对能够良好协同。我们展示了IIFE相对于现有算法的优越性能。我们还展示了交互信息如何用于改进现有的AutoFE算法。最后,我们指出了现有AutoFE文献中几个关键的实验设置问题及其对性能的影响。

英文摘要:

Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance. While traditional feature engineering requires significant domain expertise and time-consuming iterative testing, AutoFE strives to make feature engineering easy and accessible to all data science practitioners. We introduce a new AutoFE algorithm, IIFE, based on determining which feature pairs synergize well through an information-theoretic perspective called interaction information. We demonstrate the superior performance of IIFE over existing algorithms. We also show how interaction information can be used to improve existing AutoFE algorithms. Finally, we highlight several critical experimental setup issues in the existing AutoFE literature and their effects on performance.

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。

↑