用强化学习优化基因特征选择，提升生物标志物发现的准确性与稳定性。
StackFeat RL: Reinforcement Learning over Iterative Dual Criterion Feature Selection for Stable Biomarker Discovery
- 通过双重标准迭代筛选特征，避免单一准则的失效
- 在新冠和阿尔茨海默病数据上准确率最高，特征数减少3-4倍
- 适合需要稳定高维基因特征筛选的研究者
高维基因组数据（$d \gg n$）的特征选择需兼顾准确、稀疏与稳定。现有方法或需人工设定阈值（如mRMR、稳定性选择），或在数据扰动下结果不稳定（如Lasso、Boruta），或忽略生物学结构。我们提出StackFeat-RL，一种元学习框架，利用REINFORCE策略梯度优化迭代双准则特征选择算法的超参数。双准则要求系数一致性与选择频率，防范单准则方法遗漏的两类失败模式；迭代累积则通过大数定律提供收敛保证。在新冠miRNA数据（GSE240888，332个特征）及三个阿尔茨海默病分类任务（GSE84422，13237个基因；正常 vs. 可能、可能、确诊AD）中，StackFeat-RL在所有对比方法（包括ElasticNet、Boruta、mRMR、稳定性选择）中预测准确率最高，且所需特征数减少3–4倍。
原文摘要 · Abstract (English)
Feature selection in high-dimensional genomic data ($d \gg n$) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches either require manual threshold specification (mRMR, stability selection), produce unstable selections under data perturbation (Lasso, Boruta), or ignore biological structure entirely. We introduce StackFeat-RL, a meta-learning framework that optimises the hyperparameters of an iterative dual-criterion feature selection algorithm via REINFORCE policy gradients. The dual criterion, requiring both coefficient consistency and selection frequency, guards against two failure modes missed by single-criterion methods, while iterative accumulation provides convergence guarantees via the law of large numbers. On COVID-19 miRNA data (GSE240888, 332 features) and three Alzheimer's disease classification tasks (GSE84422, 13237 genes; Normal vs.\ Possible, Probable, and Definite AD), StackFeat-RL achieves the highest predictive accuracy among all evaluated methods, including ElasticNet, Boruta, mRMR, and stability selection, while requiring 3--4$\times$ fewer features. Keywords: feature selection, reinforcement learning, REINFORCE, elastic net, biomarker discovery, Alzheimer's disease, dual-criterion selection, protein interaction networks
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。