WebFed: Cross-platform Federated Learning Framework Based on Web Browser with Local Differential Privacy

TL;DR

WebFed introduces a browser-based federated learning framework that simplifies deployment across platforms and enhances privacy using local differential privacy, demonstrated through experiments on diverse devices.

Contribution

It presents a novel, browser-based federated learning framework leveraging web features and local differential privacy, reducing deployment complexity.

Findings

Effective on heterogeneous devices

Simplifies federated learning deployment

Enhances privacy with local differential privacy

Abstract

For data isolated islands and privacy issues, federated learning has been extensively invoking much interest since it allows clients to collaborate on training a global model using their local data without sharing any with a third party. However, the existing federated learning frameworks always need sophisticated condition configurations (e.g., sophisticated driver configuration of standalone graphics card like NVIDIA, compile environment) that bring much inconvenience for large-scale development and deployment. To facilitate the deployment of federated learning and the implementation of related applications, we innovatively propose WebFed, a novel browser-based federated learning framework that takes advantage of the browser's features (e.g., Cross-platform, JavaScript Programming Features) and enhances the privacy protection via local differential privacy mechanism. Finally, We conduct experiments on heterogeneous devices to evaluate the performance of the proposed WebFed framework.