Non-IID Quantum Federated Learning with One-shot Communication Complexity

TL;DR

This paper investigates quantum federated learning with non-IID data, providing a theoretical framework and demonstrating that one-shot communication can effectively address data heterogeneity, outperforming traditional methods.

Contribution

It introduces a novel quantum federated learning framework for non-IID data using one-shot communication, with theoretical decomposition of global channels into local ones.

Findings

Proves global quantum channels can be decomposed into local channels.

Develops a framework for one-shot quantum federated learning on non-IID data.

Numerical results show significant performance improvements over conventional methods.

Abstract

Federated learning refers to the task of machine learning based on decentralized data from multiple clients with secured data privacy. Recent studies show that quantum algorithms can be exploited to boost its performance. However, when the clients' data are not independent and identically distributed (IID), the performance of conventional federated algorithms is known to deteriorate. In this work, we explore the non-IID issue in quantum federated learning with both theoretical and numerical analysis. We further prove that a global quantum channel can be exactly decomposed into local channels trained by each client with the help of local density estimators. This observation leads to a general framework for quantum federated learning on non-IID data with one-shot communication complexity. Numerical simulations show that the proposed algorithm outperforms the conventional ones significantly under non-IID settings.