Hybrid Quantum Temporal Convolutional Networks

2026-02-27

AI Summary

This work addresses the scalability bottleneck of quantum machine learning in modeling complex multivariate time series. To overcome this challenge, the authors propose a parameter-efficient hybrid architecture that integrates classical temporal windowing with a quantum convolutional neural network. By sharing quantum circuits across the time dimension, the model effectively captures long-range dependencies while significantly reducing the number of trainable parameters. The shared quantum convolutional kernels process multidimensional temporal signals in a resource-efficient manner, enhancing both performance and parameter efficiency. Experimental results demonstrate that the proposed method outperforms all classical baselines on the NARMA sequence and high-dimensional EEG datasets, achieving superior accuracy with fewer parameters—particularly excelling in data-scarce scenarios.

Technology Category

• Machine Learning: Quantum Machine Learning
• Natural Language Processing: Learning & Optimization for NLP
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• quantum machine learning
• multivariate time-series
• scalability
• parameter efficiency
• long-range dependencies

Innovation

• Hybrid Quantum Temporal Convolutional Network
• quantum machine learning
• time-series analysis
• parameter efficiency
• multivariate signals