Scalable Quantum Machine Learning via Multi-layer Fully-Connected Variational Quantum Circuits

TL;DR

This paper introduces a modular multi-layer quantum circuit framework that enhances scalability and performance in quantum machine learning tasks by decomposing inputs into local blocks.

Contribution

The proposed FC-VQC framework enables scalable, trainable quantum models with linear parameter growth, outperforming monolithic circuits and matching deep neural network performance.

Findings

FC-VQC improves over monolithic VQC baselines.

Achieves competitive or better performance than DNNs.

Uses fewer trainable parameters for similar tasks.

Abstract

Variational Quantum Circuits (VQC) are promising models for quantum machine learning, but standard monolithic architectures face an expressivity--trainability dilemma: small circuits can be under-parameterized, while larger circuits are difficult to simulate and optimize. We propose Multi-Layer Fully-Connected Variational Quantum Circuits (FC-VQC), a modular framework that decomposes high-dimensional inputs into fixed-size local VQC blocks connected by deterministic block-mixing rules. This design keeps each quantum computation local while allowing the number of trainable quantum parameters to scale linearly with input dimension. We evaluate FC-VQC across tabular regression, tabular classification, and spatio-temporal BSDE/PDE approximation. Across the evaluated tasks, FC-VQC improves over monolithic VQC baselines and achieves competitive or improved performance relative to structure-matched deep neural network (DNN) baselines, while using substantially fewer trainable parameters.