Philosophy

Federated learning

Cartography

Computer security

Convergence (economics)

Economics

Set (abstract data type)

Data mining

Computer science

Simple (philosophy)

Embedding

Distributed computing

Computer network

Mathematics

Geography

Image (mathematics)

Asynchronous communication

Epistemology

Rate of convergence

Artificial intelligence

Geometry

Train

Programming language

Economic growth

Regular polygon

Key (lock)

arXiv (Cornell University)

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.

VAFL: a Method of Vertical Asynchronous Federated Learning