智能科学与技术学报2024，Vol.6Issue(1)：64-75,12.DOI:10.11959/j.issn.2096-6652.202345
基于人在回路的纵向联邦学习模型可解释性研究
Research on the explainability of vertical federated learning models based on human-in-the-loop
摘要
Abstract
Vertical federated learning(VFL)is commonly used for cross-domain data sharing in high-risk scenarios.Us-ers need to understand and trust model decisions to promote the application of models.Existing research primarily fo-cuses on the trade-off between explainability and privacy within VFL,and fails to fully meet the needs of users for estab-lishing trust and fine-tuning models.To address these issues,we proposed an explainable vertical federated learning method based on human-in-the-loop(XVFL-HITL),which incorporated user feedback into the VFL's Shapley value-based explainability approach through a distributed HITL structure,using the knowledge of all VFL participants to correct training data and enhance model performance.Furthermore,considering privacy concerns,this paper employed the addi-tive principle of Shapley values to integrate the feature contribution values of all entities other than the target participant into an aggregated measure,which effectively protected the feature privacy of each participant.Experimental results indi-cated that on benchmark data,the explainability results of XVFL-HITL were effective and could well protect the feature privacy of user.Additionally,compared to VFL-Random and VFL-Shapley,the model accuracy of XVFL-HITL improved by approximately 14%and 11%,respectively.关键词
纵向联邦学习/可解释性/人在回路/Shapley值Key words
vertical federated learning/explainability/human-in-the-loop/Shapley value分类
信息技术与安全科学引用本文复制引用
李晓欢,郑钧柏,康嘉文,叶进,陈倩..基于人在回路的纵向联邦学习模型可解释性研究[J].智能科学与技术学报,2024,6(1):64-75,12.基金项目
国家自然科学基金项目(No.U22A2054) （No.U22A2054）
广西科技重大专项(No.AA22068101)The National Natural Science Foundation of China(No.U22A2054),The Key Science and Technology Project of Guangxi(No.AA22068101) （No.AA22068101）
