论文标题
非IID量子联合学习具有一声通信复杂性
Non-IID Quantum Federated Learning with One-shot Communication Complexity
论文作者
论文摘要
联合学习是指基于有安全数据隐私的多个客户的分散数据的机器学习任务。最近的研究表明，可以利用量子算法来提高其性能。但是，当客户的数据不是独立且分布相同（IID）时，已知常规联合算法的性能会恶化。在这项工作中，我们通过理论和数值分析探索了量子联合学习中的非IID问题。我们进一步证明，借助局部密度估计器的帮助，可以将全球量子通道完全分解为由每个客户培训的本地通道。该观察结果导致了具有一声通信复杂性的非IID数据的量子联合学习的一般框架。数值模拟表明，在非IID设置下，所提出的算法比传统的算法明显优于传统算法。
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.
