[论文] Advancing Interaction-Sensitive Feature Selection: Novel Relief-Based ...

论文概要

研究领域: ML 作者: Kia Kazemi-Nia, Harsh Bandhey, Philip J. Freda, Ryan J. Urbanowicz 发布时间: 2026-08-28 arXiv: 2608.28552

中文摘要

作为高维生物医学数据建模的前奏，可靠的特征选择可以降低计算开销、提高建模性能并产生更简单、更可解释的模型。然而，大多数基于过滤器的特征选择方法难以检测特征交互，而包装器或嵌入式特征选择方法计算成本高昂。基于Relief的算法（RBA）是对特征交互敏感的过滤器方法，同时缓解了这些其他限制。本研究（1）重构、优化和扩展了scikit-rebate Python包，包含现有和新提出的RBA变体；（2）在多样化的基因组模拟中进行了严格的RBA基准比较。我们将scikit-rebate扩展为包含SWRF*、mu-Relief和5个新的RBA变体，实现了邻居选择和特征评分的替代策略。所有RBA在样本量、特征数量、遗传力和基础关联类型（如主效应和交互）变化的模拟基因组数据集上进行了评估，以比较预测特征排序和运行时间。除mu-Relief外，所有RBA都擅长检测噪声数据中的2-way交互。使用'远'评分的RBA最擅长检测2-way交互——MultiSWRFDB*表现最佳——但对主效应的敏感度低得多。SWRF、MultiSWRF、MultiSURF和MultiSWRFDB在主效应和2-way交互数据集上表现最佳，当同时考虑3-way交互时MultiSWRFDB表现最佳。scikit-rebate的重构使RBA运行时间减少了10到35倍。新引入的RBA是表现最强的之一，通过稳健地保留主效应和2-way表观遗传交互，这些算法为下游建模保留了预测信号。

原文摘要

As a precursor to high-dimensional biomedical data modeling, reliable feature selection can reduce computational expense, improve modeling performance, and yield simpler, more interpretable models. However, most filter-based feature selection methods struggle to detect feature interactions, while wrapper or embedded feature selection methods are computationally expensive. Relief-based algorithms (RBAs) are filter methods that are sensitive to feature interactions while mitigating these other limitations. This study (1) refactors, optimizes, and expands the scikit-rebate Python package with existing and newly proposed RBA variants and (2) conducts rigorous RBA benchmark comparisons across diverse genomic simulations. We expand scikit-rebate to include SWRF*, mu-Relief, and 5 novel RBA varia...

#论文 #arXiv #ML #小凯