We empirically show that process-based Parallelism speeds up the Genetic Algorithm (GA) for Feature Selection (FS) 2x to 25x, while additionally increasing the Machine Learning (ML) model performance on metrics such as F1-score, Accuracy, and Receiver Operating Characteristic Area Under the Curve (ROC-AUC).

翻译：我们通过实验表明，基于进程的并行化可将特征选择(FS)中的遗传算法(GA)速度提升2至25倍，同时还能提高机器学习(ML)模型在F1分数、准确率以及受试者工作特征曲线下面积(ROC-AUC)等指标上的表现。