Federated Quantum Kernel-Based Long Short-term Memory for Human Activity Recognition

TL;DR

This paper presents Fed-QK-LSTM, a federated learning framework combining quantum kernel methods and LSTM for improved privacy-preserving human activity recognition, demonstrating competitive accuracy in real-world edge computing scenarios.

Contribution

The paper introduces a novel federated quantum kernel-based LSTM architecture for human activity recognition, integrating quantum computing with federated learning for privacy and efficiency.

Findings

Achieves competitive accuracy on real-world HAR dataset.

Effectively models complex non-linear relationships with fewer parameters.

Demonstrates robustness in privacy-sensitive, edge computing environments.

Abstract

In this work, we introduce the Federated Quantum Kernel-Based Long Short-term Memory (Fed-QK-LSTM) framework, integrating the quantum kernel methods and Long Short-term Memory into federated learning. Within Fed-QK-LSTM framework, we enhance human activity recognition (HAR) in privacy-sensitive environments and leverage quantum computing for distributed learning systems. The DeepConv-QK-LSTM architecture on each client node employs convolutional layers for efficient local pattern capture, this design enables the use of a shallow QK-LSTM to model long-range relationships within the HAR data. The quantum kernel method enables the model to capture complex non-linear relationships in multivariate time-series data with fewer trainable parameters. Experimental results on RealWorld HAR dataset demonstrate that Fed-QK-LSTM framework achieves competitive accuracy across different client settings and local training rounds. We showcase the potential of Fed-QK-LSTM framework for robust and privacy-preserving human activity recognition in real-world applications, especially in edge computing environments and on scarce quantum devices.