FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps

TL;DR

FLSys is a mobile-cloud federated learning system designed for smartphones that supports multiple models, ensures privacy, and is scalable, aiming to foster an open ecosystem for FL apps and models.

Contribution

The paper introduces FLSys, a modular, scalable federated learning system for mobile devices with privacy features and support for concurrent models, implemented on Android and AWS.

Findings

FLSys achieves good model utility in real-world tests.

Supports concurrent training of different DL models.

Demonstrates scalability and resource efficiency.

Abstract

This article presents the design, implementation, and evaluation of FLSys, a mobile-cloud federated learning (FL) system, which can be a key component for an open ecosystem of FL models and apps. FLSys is designed to work on smart phones with mobile sensing data. It balances model performance with resource consumption, tolerates communication failures, and achieves scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. Furthermore, FLSys provides advanced privacy preserving mechanisms and a common API for third-party app developers to access FL models. FLSys adopts a modular design and is implemented in Android and AWS cloud. We co-designed FLSys with a human activity recognition (HAR) model. HAR sensing data was collected in the wild from 100+ college students during a 4-month period. We implemented HAR-Wild, a CNN model tailored to mobile devices, with a data augmentation mechanism to mitigate the problem of non-Independent and Identically Distributed data. A sentiment analysis model is also used to demonstrate that FLSys effectively supports concurrent models. This article reports our experience and lessons learned from conducting extensive experiments using simulations, Android/Linux emulations, and Android phones that demonstrate FLSys achieves good model utility and practical system performance.