Improving Response Time of Home IoT Services in Federated Learning

TL;DR

This paper enhances federated learning for home IoT services by introducing local control methods with transfer learning and differential privacy, significantly reducing response time and maintaining high accuracy despite data limitations.

Contribution

It proposes a novel local IoT control approach using federated learning with transfer learning and privacy measures to improve response time and accuracy in home IoT services.

Findings

Response time reduced to less than 1 second.

Achieved 97% accuracy with 9,000 samples.

Improved privacy and data scarcity handling.

Abstract

For intelligent home IoT services with sensors and machine learning, we need to upload IoT data to the cloud server which cannot share private data for training. A recent machine learning approach, called federated learning, keeps user data on the device in the distributed computing environment. Though federated learning is useful for protecting privacy, it experiences poor performance in terms of the end-to-end response time in home IoT services, because IoT devices are usually controlled by remote servers in the cloud. In addition, it is difficult to achieve the high accuracy of federated learning models due to insufficient data problems and model inversion attacks. In this paper, we propose a local IoT control method for a federated learning home service that recognizes the user behavior in the home network quickly and accurately. We present a federated learning client with transfer learning and differential privacy to solve data scarcity and data model inversion attack problems. From experiments, we show that the local control of home IoT devices for user authentication and control message transmission by the federated learning clients improves the response time to less than 1 second. Moreover, we demonstrate that federated learning with transfer learning achieves 97% of accuracy under 9,000 samples, which is only 2% of the difference from centralized learning.