Hybrid Quantum Temporal Convolutional Networks

TL;DR

The paper introduces HQTCN, a hybrid quantum-classical model for sequential data that captures long-range dependencies efficiently and performs well on multivariate time-series, especially with limited data.

Contribution

It presents the first hybrid quantum temporal convolutional network combining classical windowing with quantum circuits, reducing parameters while maintaining high performance.

Findings

HQTCN performs competitively on univariate data.

HQTCN outperforms classical models on multivariate data.

HQTCN maintains high accuracy with fewer parameters.

Abstract

Quantum machine learning models for sequential data face scalability challenges with complex multivariate signals. We introduce the Hybrid Quantum Temporal Convolutional Network (HQTCN), which combines classical temporal windowing with a quantum convolutional neural network core. By applying a shared quantum circuit across temporal windows, HQTCN captures long-range dependencies while achieving significant parameter reduction. Evaluated on synthetic NARMA sequences and high-dimensional EEG time-series, HQTCN performs competitively with classical baselines on univariate data and outperforms all baselines on multivariate tasks. The model demonstrates particular strength under data-limited conditions, maintaining high performance with substantially fewer parameters than conventional approaches. These results establish HQTCN as a parameter-efficient approach for multivariate time-series analysis.