A Secure and Efficient Federated Learning Framework for NLP

TL;DR

This paper introduces SEFL, a secure, efficient federated learning framework for NLP that eliminates trusted entities, maintains high accuracy, and is resilient to client dropouts, with significant runtime improvements.

Contribution

SEFL is a novel federated learning framework that removes the need for trusted aggregators and enhances efficiency and robustness in NLP tasks.

Findings

SEFL achieves comparable accuracy to existing FL solutions.

Pruning technique improves runtime performance up to 13.7x.

SEFL is resilient to client dropouts.

Abstract

In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks. Existing solutions either involve a trusted aggregator or require heavyweight cryptographic primitives, which degrades performance significantly. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient FL framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts. Through extensive experimental studies on natural language processing (NLP) tasks, we demonstrate that the SEFL achieves comparable accuracy compared to existing FL solutions, and the proposed pruning technique can improve runtime performance up to 13.7x.