Private Federated Learning In Real World Application -- A Case Study

TL;DR

This paper demonstrates a real-world implementation of private federated learning on edge devices, showcasing its effectiveness in training accurate models while preserving user privacy through a novel framework and architecture.

Contribution

Introduces a practical federated learning framework with a neural network architecture for privacy-preserving app selection, validated through simulations and on-device experiments.

Findings

PFL improves model accuracy over time by adapting to user behavior.

The framework maintains privacy by keeping data on devices and only sharing model updates.

Feasibility of deploying PFL in real-world edge scenarios is demonstrated.

Abstract

This paper presents an implementation of machine learning model training using private federated learning (PFL) on edge devices. We introduce a novel framework that uses PFL to address the challenge of training a model using users' private data. The framework ensures that user data remain on individual devices, with only essential model updates transmitted to a central server for aggregation with privacy guarantees. We detail the architecture of our app selection model, which incorporates a neural network with attention mechanisms and ambiguity handling through uncertainty management. Experiments conducted through off-line simulations and on device training demonstrate the feasibility of our approach in real-world scenarios. Our results show the potential of PFL to improve the accuracy of an app selection model by adapting to changes in user behavior over time, while adhering to privacy standards. The insights gained from this study are important for industries looking to implement PFL, offering a robust strategy for training a predictive model directly on edge devices while ensuring user data privacy.