[Paper Review] Towards Quantum Federated Learning

Chaoyu Ren, Rudai Yan+10 more|arXiv (Cornell University)|Jun 16, 2023

Quantum Computing Algorithms and Architecture12 citations

TL;DR

This paper surveys the emerging field of Quantum Federated Learning (QFL), providing a comprehensive taxonomy, state-of-the-art principles, challenges, and future directions.

ABSTRACT

Quantum Federated Learning (QFL) is an emerging interdisciplinary field that merges the principles of Quantum Computing (QC) and Federated Learning (FL), with the goal of leveraging quantum technologies to enhance privacy, security, and efficiency in the learning process. Currently, there is no comprehensive survey for this interdisciplinary field. This review offers a thorough, holistic examination of QFL. We aim to provide a comprehensive understanding of the principles, techniques, and emerging applications of QFL. We discuss the current state of research in this rapidly evolving field, identify challenges and opportunities associated with integrating these technologies, and outline future directions and open research questions. We propose a unique taxonomy of QFL techniques, categorized according to their characteristics and the quantum techniques employed. As the field of QFL continues to progress, we can anticipate further breakthroughs and applications across various industries, driving innovation and addressing challenges related to data privacy, security, and resource optimization. This review serves as a first-of-its-kind comprehensive guide for researchers and practitioners interested in understanding and advancing the field of QFL.

Motivation & Objective

• Define the scope and motivation for Quantum Federated Learning (QFL).
• Provide a holistic understanding of QFL principles, techniques, and applications.
• Identify challenges and opportunities in integrating quantum technologies with federated learning.
• Propose a taxonomy of QFL techniques based on characteristics and quantum techniques used.
• Outline future directions and open research questions in QFL.

Proposed method

• Propose a unique taxonomy of QFL techniques categorized by their characteristics and the quantum techniques employed.
• Synthesize current state-of-the-art research to map principles, techniques, and applications of QFL.
• Discuss challenges, opportunities, and open research questions in the interdisciplinary area of QC and FL.

Experimental results

Research questions

• RQ1 What are the core principles and architectures underpinning Quantum Federated Learning?
• RQ2 What taxonomy best captures the diversity of QFL techniques and quantum approaches?
• RQ3 What are the main challenges and opportunities in implementing QFL across industries?
• RQ4 What future directions and open research questions drive advancement in QFL?

Key findings

• QFL is an emerging interdisciplinary field blending quantum computing and federated learning to address privacy, security, and efficiency.
• A taxonomy of QFL techniques is proposed, organized by their characteristics and the quantum methods employed.
• The field faces challenges and opportunities related to integrating quantum technologies with federated learning.
• The review outlines future directions and open questions to guide researchers and practitioners.