DeepAI AI Chat
Log In Sign Up

Constrained Differentially Private Federated Learning for Low-bandwidth Devices

by   Raouf Kerkouche, et al.

Federated learning becomes a prominent approach when different entities want to learn collaboratively a common model without sharing their training data. However, Federated learning has two main drawbacks. First, it is quite bandwidth inefficient as it involves a lot of message exchanges between the aggregating server and the participating entities. This bandwidth and corresponding processing costs could be prohibitive if the participating entities are, for example, mobile devices. Furthermore, although federated learning improves privacy by not sharing data, recent attacks have shown that it still leaks information about the training data. This paper presents a novel privacy-preserving federated learning scheme. The proposed scheme provides theoretical privacy guarantees, as it is based on Differential Privacy. Furthermore, it optimizes the model accuracy by constraining the model learning phase on few selected weights. Finally, as shown experimentally, it reduces the upstream and downstream bandwidth by up to 99.9 learning, making it practical for mobile systems.


page 1

page 2

page 3

page 4


Federated Learning in Adversarial Settings

Federated Learning enables entities to collaboratively learn a shared pr...

Compression Boosts Differentially Private Federated Learning

Federated Learning allows distributed entities to train a common model c...

A Graph Federated Architecture with Privacy Preserving Learning

Federated learning involves a central processor that works with multiple...

One-Shot Federated Learning with Neuromorphic Processors

Being very low power, the use of neuromorphic processors in mobile devic...

Federated Remote Physiological Measurement with Imperfect Data

The growing need for technology that supports remote healthcare is being...

Privacy-Preserving Wireless Federated Learning Exploiting Inherent Hardware Impairments

We consider a wireless federated learning system where multiple data hol...

A Federated Learning Approach for Mobile Packet Classification

In order to improve mobile data transparency, a number of network-based ...