arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.21780cs.LGquant-ph
收藏

量子乐高学习:一种用于混合人工智能的模块化设计原则

Quantum LEGO Learning: A Modular Design Principle for Hybrid Artificial Intelligence

School of Electrical and Computer Engineering, Georgia Institute of Technology(电子与计算机工程学院,佐治亚理工学院);NVIDIA Research(NVIDIA研究);IBM Research(IBM研究);Hon Hai (Foxconn) Quantum Computing Research Center(鸿海(富士康)量子计算研究中心);Biomedical Engineering and Imaging Sciences, King's College London(生物医学工程与成像科学,伦敦国王学院);Computer, Electrical, and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology(计算机、电子和数学科学与工程系,国王阿卜杜勒-阿齐兹大学)

Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hsiu Hsieh, Hector Zenil, Jesper Tegner

AI总结:

本研究提出量子乐高学习框架,通过模块化设计实现混合人工智能的高效学习,强调量子与经典模块的分离与可组合性,提升泛化能力和鲁棒性。

摘要:

混合量子-经典学习模型越来越多地将神经网络与变分量子电路(VQCs)结合,以利用互补的归纳偏置。然而,许多现有方法依赖于紧密耦合的架构或任务特定的编码器,限制了概念的清晰性、通用性和在不同学习设置中的可转移性。在本工作中,我们引入了量子乐高学习,一种模块化且架构无关的学习框架,将经典和量子组件视为可重用、可组合的学习模块,具有明确的角色。在此框架中,预训练的经典神经网络充当冻结的特征模块,而VQC则作为可训练的适应模块,操作于结构化的表示而非原始输入。这种分离使在受限的量子资源下能够高效学习,并为混合模型提供了一种原理性的抽象。我们开发了一种基于块的泛化理论,将学习误差分解为近似和估计成分,明确刻画了每个模块的复杂性和训练状态如何影响整体性能。我们的分析推广了先前张量网络特定的结果,并确定了量子模块在与同等大小的经典头部相比时提供表征优势的条件。通过系统地进行块交换实验,我们验证了该框架在冻结特征提取器和量子和经典适应头部上的有效性。在量子点分类实验中,展示了稳定的优化、减少对量子位数量的敏感性以及对现实噪声的鲁棒性。

英文摘要:

Hybrid quantum-classical learning models increasingly integrate neural networks with variational quantum circuits (VQCs) to exploit complementary inductive biases. However, many existing approaches rely on tightly coupled architectures or task-specific encoders, limiting conceptual clarity, generality, and transferability across learning settings. In this work, we introduce Quantum LEGO Learning, a modular and architecture-agnostic learning framework that treats classical and quantum components as reusable, composable learning blocks with well-defined roles. Within this framework, a pre-trained classical neural network serves as a frozen feature block, while a VQC acts as a trainable adaptive module that operates on structured representations rather than raw inputs. This separation enables efficient learning under constrained quantum resources and provides a principled abstraction for analyzing hybrid models. We develop a block-wise generalization theory that decomposes learning error into approximation and estimation components, explicitly characterizing how the complexity and training status of each block influence overall performance. Our analysis generalizes prior tensor-network-specific results and identifies conditions under which quantum modules provide representational advantages over comparably sized classical heads. Empirically, we validate the framework through systematic block-swap experiments across frozen feature extractors and both quantum and classical adaptive heads. Experiments on quantum dot classification demonstrate stable optimization, reduced sensitivity to qubit count, and robustness to realistic noise.

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。

↑