VAFL: a Method of Vertical Asynchronous Federated Learning

TL;DR

This paper introduces VAFL, a novel asynchronous vertical federated learning method that enables clients to independently update models, ensuring data privacy and communication efficiency, with proven convergence and empirical success on diverse datasets.

Contribution

The paper proposes VAFL, a simple asynchronous vertical FL approach with perturbed local embeddings, offering convergence guarantees and enhanced privacy and efficiency.

Findings

Converges for strongly convex, nonconvex, nonsmooth objectives.

Achieves comparable or better performance than centralized and synchronous FL.

Ensures data privacy through perturbed local embeddings.

Abstract

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.