arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.21749quant-phcs.LG
收藏

混合量子神经网络中的模型选择及其在量子变换器架构中的应用

Model selection in hybrid quantum neural networks with applications to quantum transformer architectures

Quantum Lab, Fujitsu Research of India(Fujitsu印度研究量子实验室)

Harsh Wadhwa, Rahul Bhowmick, Naipunnya Raj, Rajiv Sangle, Ruchira V. Bhat, Krishnakumar Sabapathy

AI总结:

本文提出QBET工具箱,通过简洁指标评估量子、经典和混合变换器架构,实现高效模型筛选,提升量子自注意力在分类和生成任务中的性能。

摘要:

量子机器学习模型通常缺乏系统设计指南,通常需要资源密集型训练来寻找有效配置。为解决这一挑战,我们开发了量子偏置-表达力工具箱(QBET),用于评估量子、经典和混合变换器架构。在该工具箱中,我们引入了简洁指标用于比较不同模型,并扩展了偏置(SB)的分析到生成和多类分类任务。我们展示QBET能够高效筛选有前途的模型变体,无需执行完整训练流程。在基于变换器的分类和生成任务评估中,我们使用总共18个量子比特用于嵌入(每个查询、键、值各6个量子比特)。我们识别出量子自注意力变体在某些场景下超越经典对应物,通过根据SB指标排名模型并比较其相对性能。

英文摘要:

Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox ($\texttt{QBET}$), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias ($\texttt{SB}$) and Expressivity ($\texttt{EXP}$), for comparing across various models, and extend the analysis of $\texttt{SB}$ to generative and multiclass-classification tasks. We show that $\texttt{QBET}$ enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of $18$ qubits for embeddings ($6$ qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the $\texttt{SB}$ metric and comparing their relative performance.

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。

↑