arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.08217cs.AI
收藏

面向多模态数据的量子联邦学习:一种模态无关方法

Quantum Federated Learning for Multimodal Data: A Modality-Agnostic Approach

Department of Electrical and Computer Engineering, The University of Alabama in Huntsville(电气与计算机工程系,阿拉巴马大学亨茨维尔分校)

Atit Pokharel, Ratun Rahman, Thomas Morris, Dinh C. Nguyen

AI总结:

提出一种利用量子纠缠进行中间融合的多模态量子联邦学习方法,并通过 MMA 机制隔离未训练量子电路以应对模态缺失,在 IID 与非 IID 设置下分别提升准确率 6.84% 和 7.25%。

摘要:

量子联邦学习(QFL)最近被提出,用于在多个量子处理器(客户端)之间实现分布式、隐私保护的量子机器学习(QML)模型训练。尽管近期已有研究努力,但现有 QFL 框架主要集中于单模态系统,限制了其在现实任务中的适用性,因为这些任务通常自然涉及多种模态。为填补这一重要空白,我们首次提出一种专门为 QFL 场景设计的新型多模态方法,该方法利用量子纠缠进行中间融合。此外,为解决多模态 QFL 中的一个主要瓶颈,即训练期间某些模态缺失可能降低模型性能,我们引入了 Missing Modality Agnostic(MMA,缺失模态无关)机制,该机制隔离未经训练的量子电路,从而在不产生损坏状态的情况下确保稳定训练。仿真结果表明,与最先进方法相比,所提出的带 MMA 的多模态 QFL 方法在独立同分布(IID)数据分布上准确率提升 6.84%,在非 IID 数据分布上准确率提升 7.25%。

英文摘要:

Quantum federated learning (QFL) has been recently introduced to enable a distributed privacy-preserving quantum machine learning (QML) model training across quantum processors (clients). Despite recent research efforts, existing QFL frameworks predominantly focus on unimodal systems, limiting their applicability to real-world tasks that often naturally involve multiple modalities. To fill this significant gap, we present for the first time a novel multimodal approach specifically tailored for the QFL setting with the intermediate fusion using quantum entanglement. Furthermore, to address a major bottleneck in multimodal QFL, where the absence of certain modalities during training can degrade model performance, we introduce a Missing Modality Agnostic (MMA) mechanism that isolates untrained quantum circuits, ensuring stable training without corrupted states. Simulation results demonstrate that the proposed multimodal QFL method with MMA yields an improvement in accuracy of 6.84% in independent and identically distributed (IID) and 7.25% in non-IID data distributions compared to the state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑