Abstract
Long short-term memory (LSTM) models are a particular type of recurrent neural networks (RNNs) that are central to sequential modeling tasks in domains such as urban telecommunication forecasting, where temporal correlations and nonlinear dependencies dominate. However, conventional LSTMs suffer from high parameter redundancy and limited nonlinear expressivity. In this work, we propose the Quantum-inspired Kolmogorov-Arnold Long Short-Term Memory (QKAN-LSTM), which integrates Data Re-Uploading Activation (DARUAN) modules into the gating structure of LSTMs. Each DARUAN acts as a quantum variational activation function (QVAF), enhancing frequency adaptability and enabling an exponentially enriched spectral representation without multi-qubit entanglement. The resulting architecture preserves quantum-level expressivity while remaining fully executable on classical hardware. Empirical evaluations on three datasets, Damped Simple Harmonic Motion, Bessel Function, and Urban Telecommunication, demonstrate that QKAN-LSTM achieves superior predictive accuracy and generalization with a 79% reduction in trainable parameters compared to classical LSTMs. We extend the framework to the Jiang-Huang-Chen-Goan Network (JHCG Net), which generalizes KAN to encoder-decoder structures, and then further use QKAN to realize the latent KAN, thereby creating a Hybrid QKAN (HQKAN) for hierarchical representation learning. The proposed HQKAN-LSTM thus provides a scalable and interpretable pathway toward quantum-inspired sequential modeling in real-world data environments.
Abstract (translated)
长短期记忆（LSTM）模型是一种特别类型的递归神经网络（RNN），在诸如城市电信预测等领域中用于序列建模任务，这些领域中的时间相关性和非线性依赖关系占主导地位。然而，传统的LSTM模型存在参数冗余高和非线性表达能力有限的问题。为此，我们提出了一种量子启发的Kolmogorov-Arnold长短期记忆（QKAN-LSTM）模型，该模型将数据重新上传激活（DARUAN）模块整合到LSTM的门控结构中。每个DARUAN作为一个量子变分激活函数（QVAF），增强了频率适应性，并在没有多量子位纠缠的情况下实现了指数级丰富的谱表示。这种架构保留了量子级别的表达能力，同时完全可以在经典硬件上执行。 通过三个数据集——阻尼简谐运动、贝塞尔函数和城市电信的数据进行的实证评估表明，QKAN-LSTM比传统的LSTMs模型减少了79%的可训练参数，并且在预测准确性和泛化性方面表现出色。我们还扩展了Jiang-Huang-Chen-Goan网络（JHCG Net）框架，该框架将KAN推广到了编码器-解码器结构中，然后进一步使用QKAN实现潜在的KAN，从而创建了一个混合型QKAN（HQKAN），用于层次表示学习。因此，所提出的HQKAN-LSTM为在实际数据环境中进行量子启发式的序列建模提供了一条可扩展且易于解释的道路。 这个研究工作表明了量子计算理念如何可以被应用于传统的机器学习模型中以提高其性能和表达能力，尤其是在处理复杂的时间序列问题时。这种方法不仅减少了所需的参数数量，还提升了模型的预测准确性和泛化能力，这为未来将量子算法集成到经典硬件上进行高效数据处理提供了可能的方向。
URL
https://arxiv.org/abs/2512.05049
