提出量子模型筛选工具，高效识别优于经典模型的量子注意力结构。
Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
- 设计轻量级指标衡量量子模型简洁性与表达力，支持跨架构比较。
- 在18量子比特的量子自注意力任务中，发现部分量子模型性能超越经典版本。
- 适用于想快速验证量子变压器有效性的研究人员，避免盲目训练。
量子机器学习模型普遍缺乏系统的设计指导，常需在多种编码方式、量子电路设计和初始化策略中进行全量资源消耗训练以寻找有效配置。为解决此问题，我们开发了量子偏置-表达力工具箱（Quantum Bias-Expressivity Toolbox, QBET），用于评估量子、经典及混合变压器架构。该工具箱引入简洁性偏置（SB）和表达力（EXP）的轻量级度量指标，实现跨模型的高效对比，并将SB分析扩展至生成与多分类任务。实验表明，QBET可实现对潜在优秀模型变体的高效预筛选，无需执行完整训练流程。我们在基于变压器的分类与生成任务中使用共18个量子比特（查询、键、值各6比特）进行嵌入，通过SB指标排序并比较模型表现，识别出量子自注意力结构在特定场景下显著优于经典模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。