Research on differential privacy protection for Stacking algorithm
In order to solve the problem that homogeneous ensemble learning algorithms are more sensitive to noise and difficult to take into account both better predictive performance and effective priva-cy protection,a DPStacking algorithm based on differential privacy is proposed.This algorithm com-bines heterogeneous Stacking algorithms with differential privacy technology to optimize the privacy pro-tection and its predictive performance.However,since both the low-level and high-level models of the Stacking algorithm can be composed of different learners,if a privacy budget allocation scheme is de-signed for a particular learner to provide differential privacy protection,this scheme is often not applica-ble to Stacking algorithms composed of arbitrary base learners and meta-learners.Based on this,a pri-vacy budget allocation scheme based on meta-learners is designed,which allocates different privacy budgets to different components of meta-learners according to the Pearson correlation coefficient and the characteristics of differential privacy parallel combination.Through theoretical and experimental verifi-cation,DPStacking algorithm satisfies ε-differential privacy protection.Compared with differential pri-vacy random forest algorithm(DiffRFs),Adaboost algorithm(DP-AdaBoost),XGBoost algorithm(DPXGB),it can effectively guarantee data privacy while having better predictive performance,and bet-ter solve the problem that single homogeneous ensemble learning algorithm is more sensitive to noise.
万方数据
维普
