Academic

Hybrid Quantum Temporal Convolutional Networks

arXiv:2602.23578v1 Announce Type: new 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.

J
Junghoon Justin Park, Maria Pak, Sebin Lee, Samuel Yen-Chi Chen, Shinjae Yoo, Huan-Hsin Tseng, Jiook Cha · · 1 min read · 4 views
#cs.LG

arXiv:2602.23578v1 Announce Type: new 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.

Executive Summary

This article introduces the Hybrid Quantum Temporal Convolutional Network (HQTCN), a novel approach to quantum machine learning for sequential data. By combining classical temporal windowing with a quantum convolutional neural network core, HQTCN captures long-range dependencies in multivariate time-series data while achieving significant parameter reduction. Evaluated on synthetic and real-world datasets, HQTCN performs competitively with classical baselines on univariate tasks and outperforms all baselines on multivariate tasks, particularly under data-limited conditions. These results establish HQTCN as a parameter-efficient approach for multivariate time-series analysis, with potential applications in fields such as finance, healthcare, and climate modeling.

Key Points

  • ▸ HQTCN combines classical temporal windowing with a quantum convolutional neural network core
  • ▸ HQTCN captures long-range dependencies in multivariate time-series data
  • ▸ HQTCN achieves significant parameter reduction while maintaining competitive performance

Merits

Strength in Multivariate Analysis

HQTCN outperforms classical baselines on multivariate tasks, particularly under data-limited conditions

Parameter Efficiency

HQTCN achieves significant parameter reduction while maintaining competitive performance

Demerits

Scalability Challenges

HQTCN may face scalability challenges with complex multivariate signals, particularly as the number of variables increases

Expert Commentary

The introduction of HQTCN marks a significant milestone in the development of quantum machine learning for sequential data. By leveraging the strengths of both classical and quantum approaches, HQTCN offers a novel solution to the challenges of multivariate time-series analysis. However, further research is needed to address scalability challenges and to explore the potential applications of HQTCN in fields such as finance, healthcare, and climate modeling. Ultimately, HQTCN has the potential to transform the field of time-series analysis and to drive innovation in a range of industries.

Recommendations

  • ✓ Further research is needed to explore the potential applications of HQTCN in fields such as finance, healthcare, and climate modeling
  • ✓ HQTCN should be tested on a range of datasets to validate its performance and to explore its limitations

Sources

Related Articles