mlsanityData to 14 Oct 2026

Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

arXiv 2605.06734 ↗First posted 7 May 2026cs.LG cs.AI quant-phcited by 4

Not on the map. Why?

Abstract (arXiv)

Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states. Quantum FWPs (QFWPs) extend this idea with variational quantum circuits (VQCs), but existing implementations rely on multi-qubit architectures that are difficult to scale on noisy intermediate-scale quantum (NISQ) devices and expensive to simulate classically. We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN) using single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN). We further introduce a scalar-gated fast-weight update rule that stabilizes parameter evolution, supported by a theoretical analysis of its adaptive memory kernel, geometric boundedness, and parallelizable gradient paths. We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result. In the long-horizon setting with 528-month input window and 132-month forecast horizon, our 12.5k-parameter model achieves lower scaled Mean Square Error (MSE), peak amplitude error, and peak timing error than a suite of classical recurrent baselines with up to 13x more parameters, including Long Short-Term Memory (LSTM) networks (25.9k-89.1k parameters), WaveNet-LSTM (167k), Vanilla recurrent neural network (11.5k), and a Modified Echo State Network (132k). To validate NISQ compatibility, we further deploy the trained fast programmer on IonQ and IBM Quantum processors, recovering forecasting accuracy within 0.1% relative MSE of the noiseless simulator at 1024 shots. These results position gated QKAN-FWP as a scalable, parameter-efficient, and NISQ-compatible approach to quantum-inspired sequence modeling.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 88 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

44 of 88 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020Variational Quantum Algorithmscited by 692
  3. 2018Barren plateaus in quantum neural network training landscapescited by 630
  4. 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 514
  5. 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 502
  6. 2020The effect of data encoding on the expressive power of variational quantum machine learning modelscited by 333
  7. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  8. 2023Challenges and Opportunities in Quantum Machine Learningcited by 203
  9. 2019Variational Quantum Circuits for Deep Reinforcement Learningcited by 167
  10. 2024Barren Plateaus in Variational Quantum Computingcited by 133
  11. 2017Parallelizing Linear Recurrent Neural Nets Over Sequence Lengthcited by 127
  12. 2020Quantum Long Short-Term Memorycited by 120
32 more
  1. 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 98
  2. 2021Going Beyond Linear Transformers with Recurrent Fast Weight Programmerscited by 89
  3. 2020Recurrent Quantum Neural Networkscited by 80
  4. 2023Does provable absence of barren plateaus imply classical simulability?cited by 80
  5. 2020Reinforcement Learning with Quantum Variational Circuitscited by 77
  6. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 70
  7. 2024A Survey on Kolmogorov-Arnold Networkcited by 68
  8. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 55
  9. 2024Curriculum reinforcement learning for quantum architecture search under hardware errorscited by 37
  10. 2024KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Searchcited by 37
  11. 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 30
  12. 2022Quantum deep recurrent reinforcement learningcited by 24
  13. 2023Asynchronous training of quantum reinforcement learningcited by 20
  14. 2023cuQuantum SDK: A High-Performance Library for Accelerating Quantum Sciencecited by 19
  15. 2025A Practitioner's Guide to Kolmogorov-Arnold Networkscited by 18
  16. 2024Quantum Kernel-Based Long Short-term Memory for Climate Time-Series Forecastingcited by 17
  17. 2022Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learningcited by 16
  18. 2022Reservoir Computing via Quantum Recurrent Neural Networkscited by 14
  19. 2023Efficient quantum recurrent reinforcement learning via quantum reservoir computingcited by 14
  20. 2024Quantum-Train-Based Distributed Multi-Agent Reinforcement Learningcited by 14
  21. 2025Toward Large-Scale Distributed Quantum Long Short-Term Memory with Modular Quantum Computerscited by 14
  22. 2024QEEGNet: Quantum Machine Learning for Enhanced Electroencephalography Encodingcited by 13
  23. 2025Generative quantum advantage for classical and quantum problemscited by 11
  24. 2025Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networkscited by 10
  25. 2025QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memorycited by 8
  26. 2025Quantum-Enhanced Parameter-Efficient Learning for Typhoon Trajectory Forecastingcited by 7
  27. 2025Quantum-Enhanced Natural Language Generation: A Multi-Model Framework with Hybrid Quantum-Classical Architecturescited by 4
  28. 2025Exploring the Potential of QEEGNet for Cross-Task and Cross-Dataset Electroencephalography Encoding with Quantum Machine Learningcited by 3
  29. 2025Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architecturescited by 2
  30. 2025Quantum Adaptive Self-Attention for Financial Rebalancing: An Empirical Study on Automated Market Makers in Decentralized Financecited by 2
  31. 2025You Only Measure Once: On Designing Single-Shot Quantum Machine Learning Modelscited by 2
  32. 2025SOH-KLSTM: A Hybrid Kolmogorov-Arnold Network and LSTM Model for Enhanced Lithium-Ion Battery Health Monitoringcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecastingcited by 3
  2. 2026Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gatescited by 1
  3. 2026Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecastingcited by 0
  4. 2026Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scalable Quantum Reinforcement Learning on NISQ Devices with Dynamic-Circuit Qubit Reuse and Grover Optimization
  2. 2026Modeling quantum neural network gradient with reinforcement learning
  3. 2024VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
  4. 2026Learning to Program Adaptive Non-Local Observables for Machine Learning
  5. 2026Beyond Reinforcement Learning: Fast and Scalable Quantum Circuit Synthesis
  6. 2025Hybrid Reward-Driven Reinforcement Learning for Efficient Quantum Circuit Synthesis
  7. 2025Quantum Long Short-term Memory with Differentiable Architecture Search
  8. 2025Dissecting Quantum Reinforcement Learning: A Systematic Evaluation of Key Components