VAFL: a Method of Vertical Asynchronous Federated Learning

07/12/2020

∙

Horizontal Federated learning (FL) handles multi-client data that share the same set of features, and vertical FL trains a better predictor that combine all the features from different clients. This paper targets solving vertical FL in an asynchronous fashion, and develops a simple FL method. The new method allows each client to run stochastic gradient algorithms without coordination with other clients, so it is suitable for intermittent connectivity of clients. This method further uses a new technique of perturbed local embedding to ensure data privacy and improve communication efficiency. Theoretically, we present the convergence rate and privacy level of our method for strongly convex, nonconvex and even nonsmooth objectives separately. Empirically, we apply our method to FL on various image and healthcare datasets. The results compare favorably to centralized and synchronous FL methods.

READ FULL TEXT

VAFL: a Method of Vertical Asynchronous Federated Learning

Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM

Mobility Improves the Convergence of Asynchronous Federated Learning

vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer

FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning

VAFL: a Method of Vertical Asynchronous Federated Learning

Related Research

Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM

Mobility Improves the Convergence of Asynchronous Federated Learning

vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer

FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning