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

TL;DR

Quantum LEGO Learning introduces a modular framework for hybrid quantum-classical models, enabling flexible, transfer-friendly architectures that improve efficiency and robustness in quantum machine learning tasks.

Contribution

It proposes a novel modular, architecture-agnostic framework that separates classical and quantum components, with a theoretical analysis and empirical validation of its advantages.

Findings

Enhanced stability and noise robustness in quantum dot classification

Reduced sensitivity to qubit count in experiments

Theoretical decomposition of learning error into approximation and estimation components

Abstract

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.