Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation

2026-06-22

AI Summary

This work addresses the challenge of modeling variable-length sequential data in quantum computing by proposing a Recursive Quantum Long Short-Term Memory (Recursive QLSTM) model. By integrating a meta-kernel-based recursive architecture with a dynamic variational quantum circuit adaptation mechanism, the model significantly enhances its capacity to handle sequences of varying lengths, improving both temporal information propagation and generalization performance. Combining recurrent neural network structures, variational quantum circuits, and quantum machine learning techniques, the proposed approach demonstrates superior performance across diverse sequence lengths and recursion rules. Both theoretical analysis and empirical experiments corroborate its pronounced advantages in quantum recurrent learning tasks.

Abstract

Recent advances in quantum computing and machine learning have motivated the development of quantum models for sequential data processing. In this paper, we propose a Recursive Quantum Long Short-Term Memory model, or Recursive QLSTM, which extends QLSTM through metacore-based recursive constructions. We numerically test the model under different input sequence lengths, metacore designs, and recursive rules, and identify the best-performing architecture among these variants. For this selected model, we further provide theoretical arguments explaining why its recursive structure improves temporal information propagation and enhances learning performance. Our results suggest that Recursive QLSTM offers a flexible and effective framework for quantum recurrent learning over input time series of various lengths.

Problem

• quantum recurrent learning
• sequential data processing
• temporal information propagation
• quantum LSTM
• variable-length time series

Innovation

• Recursive QLSTM
• metacore-based recursion
• quantum recurrent learning
• dynamic variational quantum circuit
• temporal information propagation