基于Lightgbm和XGBoost的优化深度森林算法

谢军飞, 张海清, 李代伟, 于曦, 邓钧予

Optimized deep forest algorithm based on Lightgbm and XGBoost

Junfei Xie, Haiqing Zhang, Daiwei Li, Xi Yu, Junyu Deng

表5 LIGHT?XDF和十种对比算法在八个数据集上的算法AUC比较

Table 5 AUC of LIGHT?XDF and other ten algorithms on eight datasets

数据集 RF NB KNN SVM Lightgbm XGBoost ASTGNN ada⁃mdf lgb⁃df Gcforest LIGHT⁃XDF Chemical Engineering 0.988 0.953 0.673 0.696 0.971 0.988 0.946 0.972 0.988 0.977 0.988 EEE 0.968 0.949 0.708 0.689 0.961 0.980 0.975 0.977 0.962 0.987 0.994 Mechanical Engineering 0.959 0.918 0.633 0.619 0.945 0.972 0.982 0.919 0.972 0.959 0.973 Adult 0.766 0.809 0.777 0.620 0.797 0.798 0.742 0.769 0.793 0.784 0.790 Dry_Bean 0.957 0.862 0.835 0.786 0.958 0.956 0.892 0.946 0.959 0.949 0.959 Bank Marketing 0.684 0.716 0.622 0.505 0.734 0.730 0.674 0.672 0.726 0.695 0.708 Winequality⁃red 0.799 0.731 0.707 0.710 0.791 0.797 0.751 0.784 0.806 0.780 0.811 Winequality⁃white 0.802 0.683 0.690 0.669 0.807 0.801 0.751 0.760 0.796 0.750 0.804