Hybrid Differentially Private Federated Learning on Vertically Partitioned Data

Chang Wang
Chang Wang
Mingkai Huang
Mingkai Huang
Bing Bai
Bing Bai
Hao Li
Hao Li
Cited by: 0|Views74
Weibo:
This paper studies this issue and presents HDP-vertical federated learning, the first differentially private framework for VFL

Abstract:

We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w.r.t. training time, accuracy, etc., comparing to idealized non-private VFL. ...More

Code:

Data:

0
Full Text
Bibtex
Weibo
Your rating :
0

 

Tags
Comments