QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Quoc Bao Phan, Tuy Tan Nguyen
• Venue: arXiv: cs.LG
• Published: 2026-07-02
• Collected: 2026-07-03
• URL: http://arxiv.org/abs/2607.02426v1
• PDF: https://arxiv.org/pdf/2607.02426v1
• DOI: UNKNOWN

Plain-Language Brief

The paper proposes QFedAgent, a hybrid quantum-classical personalized Federated Learning framework for multi-agent activity recognition. It introduces a variational quantum circuit fusion module that models accelerometer-gyroscope interactions using quantum state encoding and entanglement, resulting in significant parameter reduction compared to classical methods. The experiments on the OPPORTUNITY dataset show competitive results with conventional federated learning baselines.

What the Document Says

• The text discusses a new approach called QFedAgent for multi-agent activity recognition using Federated Learning (FL).
• QFedAgent integrates a variational quantum circuit fusion module that models accelerometer-gyroscope interactions.
• This quantum fusion module uses quantum state encoding and entanglement, requiring fewer parameters than classical methods.
• The text claims that the proposed method achieves approximately 10x total parameter reduction compared to classical methods.
• Experiments were conducted on the OPPORTUNITY dataset under subject-based non-IID partitions.
• The experiments showed a mean test accuracy of 97.7% for QFedAgent, confirming its competitiveness with conventional federated learning baselines.

Key Concepts Mentioned

• Federated Learning
• Quantum Computing
• Variational Quantum Circuit
• Accelerometer-Gyroscope Interactions
• OPPORTUNITY Dataset

Claims Made by the Document

• QFedAgent achieves approximately 10x total parameter reduction compared to classical methods.
• QFedAgent shows competitive results with conventional federated learning baselines.

Evidence Used

• Experiments on the OPPORTUNITY dataset show mean test accuracy of 97.7% for QFedAgent
• Quantum fusion module requires only 72 quantum rotation parameters versus 33K in classical multi-layer perceptron-based fusion.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, making it suitable for privacy-sensitive robotic sensing applications. However, multi-agent systems generate heterogeneous and non-independent and identically distributed (non-IID) multimodal sensor streams that degrade conventional FL algorithms, while classical fusion modules introduce substantial parameter overhead and communication cost. This paper proposes QFedAgent, a hybrid quantum-classical personalized FL framework for multi-agent activity recognition. The approach integrates a variational quantum circuit fusion module that models accelerometer--gyroscope interactions through quantum state encoding and entanglement, requiring only 72 quantum rotation parameters versus 33K in classical multi-layer perceptron-based fusion, achieving approximately 10x total parameter reduction. Experiments on the OPPORTUNITY dataset under subject-based non-IID partitions demonstrate 97.7% mean test accuracy, confirming that parameter-efficient quantum fusion remains competitive with conventional federated baselines.