Quantum Kernel-Based Long Short-term Memory

Abstract

The integration of quantum computing into classical machine learning architectures has emerged as a promising approach to enhance model efficiency and computational capacity. In this work, we introduce the Quantum Kernel-Based Long Short-Term Memory (QK-LSTM) network, which utilizes quantum kernel functions within the classical LSTM framework to capture complex, non-linear patterns in sequential data. By embedding input data into a high-dimensional quantum feature space, the QK-LSTM model reduces the reliance on large parameter sets, achieving effective compression while maintaining accuracy in sequence modeling tasks. This quantum-enhanced architecture demonstrates efficient convergence, robust loss minimization, and model compactness, making it suitable for deployment in edge computing environments and resource-limited quantum devices (especially in the NISQ era). Benchmark comparisons reveal that QK-LSTM achieves performance on par with classical LSTM models, yet with fewer parameters, underscoring its potential to advance quantum machine learning applications in natural language processing and other domains requiring efficient temporal data processing.

Figures (3)

• Figure 1: Schematic representation of a standard classical LSTM cell.
• Figure 2: Overview of the QK-LSTM Architecture. (a) The QK-LSTM cell integrates quantum kernel transformations within the conventional LSTM framework, where each gate (forget, input, and output) utilizes quantum kernels to enhance sequential data processing and retain temporal dependencies. (b) The unitary gate representation of the quantum kernel, denoted as $U(x_i, w)$, maps classical input data $x_t$ into a quantum feature space, with the conjugate transpose $U^{\dagger}(x_j, w)$ facilitating quantum state overlap calculations. (c) The full quantum circuit of the QSVM, which applies quantum kernel-based transformations to encode data, aiding in quantum-enhanced machine-learning tasks within the QK-LSTM model.
• Figure 3: Training performance comparison for QLSTM, Classical, and QK-LSTM models. (a) Accuracy over epochs. (b) Loss over epochs, showing optimization trends for each model.