Related papers: QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

URL: http://arxiv.org/abs/2512.05049v1
Date: Thu, 04 Dec 2025 18:03:23 GMT
Title: QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory
Authors: Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Nan-Yow Chen, Samuel Yen-Chi Chen, En-Jui Kuo, Hsi-Sheng Goan,
Abstract summary: Long short-term memory (LSTM) models are central to sequential modeling tasks in domains such as urban telecommunication forecasting.<n>We propose the Quantum-inspired Kolmogorov-Arnold Long Short-Term Memory (QKAN-LSTM)<n>QKAN-LSTM integrates Data Re-Uploading Activation modules into the gating structure of LSTMs.
Score: 11.996286932948124
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
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.

Related papers

Subtractive Modulative Network with Learnable Periodic Activations [59.89799070130572]
We propose a novel, parameter-efficient Implicit Neural Representation architecture inspired by classical subtractive synthesis.<n>Our SMN achieves a PSNR of $40+$ dB on two image datasets, comparing favorably against state-of-the-art methods in terms of both reconstruction accuracy and parameter efficiency.
arXiv Detail & Related papers (2026-02-18T10:20:50Z)
Learning to Dissipate Energy in Oscillatory State-Space Models [51.98491034847041]
State-space models (SSMs) are a class of networks for sequence learning.<n>We show that D-LinOSS consistently outperforms previous LinOSS methods on long-range learning tasks.
arXiv Detail & Related papers (2025-05-17T23:15:17Z)
Federated Quantum-Train Long Short-Term Memory for Gravitational Wave Signal [3.360429911727189]
We present Federated QT-LSTM, a novel framework that combines the Quantum-Train (QT) methodology with Long Short-Term Memory (LSTM) networks in a federated learning setup.<n>By leveraging quantum neural networks (QNNs) to generate classical LSTM model parameters during training, the framework effectively addresses challenges in model compression, scalability, and computational efficiency.
arXiv Detail & Related papers (2025-03-20T11:34:13Z)
Quantum Kernel-Based Long Short-term Memory [0.30723404270319693]
We introduce the Quantum Kernel-Based Long Short-Term Memory (QK-LSTM) network to capture complex, non-linear patterns in sequential data. This quantum-enhanced architecture demonstrates efficient convergence, robust loss minimization, and model compactness. Benchmark comparisons reveal that QK-LSTM achieves performance on par with classical LSTM models, yet with fewer parameters.
arXiv Detail & Related papers (2024-11-20T11:39:30Z)
Unlocking the Power of LSTM for Long Term Time Series Forecasting [27.245021350821638]
We propose a simple yet efficient algorithm named P-sLSTM built upon sLSTM by incorporating patching and channel independence.<n>These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results.
arXiv Detail & Related papers (2024-08-19T13:59:26Z)
Implementation Guidelines and Innovations in Quantum LSTM Networks [2.938337278931738]
This paper presents a theoretical analysis and an implementation plan for a Quantum LSTM model, which seeks to integrate quantum computing principles with traditional LSTM networks. The actual architecture and its practical effectiveness in enhancing sequential data processing remain to be developed and demonstrated in future work.
arXiv Detail & Related papers (2024-06-13T10:26:14Z)
Federated Quantum Long Short-term Memory (FedQLSTM) [58.50321380769256]
Quantum federated learning (QFL) can facilitate collaborative learning across multiple clients using quantum machine learning (QML) models. No prior work has focused on developing a QFL framework that utilizes temporal data to approximate functions. A novel QFL framework that is the first to integrate quantum long short-term memory (QLSTM) models with temporal data is proposed.
arXiv Detail & Related papers (2023-12-21T21:40:47Z)
Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
arXiv Detail & Related papers (2023-06-19T23:10:02Z)
Towards Energy-Efficient, Low-Latency and Accurate Spiking LSTMs [1.7969777786551424]
Spiking Neural Networks (SNNs) have emerged as an attractive-temporal computing paradigm vision for complex tasks. We propose an optimized spiking long short-term memory networks (LSTM) training framework that involves a novel. rev-to-SNN conversion framework, followed by SNN training. We evaluate our framework on sequential learning tasks including temporal M, Google Speech Commands (GSC) datasets, and UCI Smartphone on different LSTM architectures.
arXiv Detail & Related papers (2022-10-23T04:10:27Z)
Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
arXiv Detail & Related papers (2022-08-28T17:50:19Z)
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
arXiv Detail & Related papers (2021-03-17T08:28:30Z)
Quantum Long Short-Term Memory [3.675884635364471]
Long short-term memory (LSTM) is a recurrent neural network (RNN) for sequence and temporal dependency data modeling. We propose a hybrid quantum-classical model of LSTM, which we dub QLSTM. Our work paves the way toward implementing machine learning algorithms for sequence modeling on noisy intermediate-scale quantum (NISQ) devices.
arXiv Detail & Related papers (2020-09-03T16:41:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.