Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
This addresses the problem of resource-intensive training in quantum machine learning for researchers, though it is incremental as it builds on existing transformer architectures.
The paper tackles the lack of principled design guidelines in quantum machine learning by developing the Quantum Bias-Expressivity Toolbox (QBET) to evaluate quantum, classical, and hybrid transformer architectures, showing that it enables efficient pre-screening of model variants and identifies scenarios where quantum self-attention surpasses classical counterparts.
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.