aiqbench analysis
This research proposes a lightweight Quantum Prototypical Recurrent Unit (QPRU) designed to outperform classical LSTMs and GRUs while using fewer parameters than existing quantum variants. The approach demonstrates competitive forecasting performance with enhanced scalability, addressing key efficiency challenges in hybrid AI-quantum architectures.
A Quantum Variational Approach to Prototypical Recurrent Unit
arXiv:2609.04354v1 Announce Type: new Abstract: We introduce a lightweight Quantum Prototypical Recurrent Unit (QPRU) that requires significantly fewer parameters than both classical recurrent architectures, such as Long Short- Term Memory (LSTM) and Gated Recurrent Unit (GRU), and quantum variants, including Quantum LSTM (QLSTM) and Quantum GRU (QGRU). Despite its compact design, the QPRU achieves competitive forecasting performance, matching state-of-the-art baselines while offering important structural and practical advantages, including enhanced scalability and a reduced number of trainable parameters.
Abstract:We introduce a lightweight Quantum Prototypical Recurrent Unit (QPRU) that requires significantly fewer parameters than both classical recurrent architectures, such as Long Short- Term Memory (LSTM) and Gated Recurrent Unit (GRU), and quantum variants, including Quantum LSTM (QLSTM) and Quantum GRU (QGRU). Despite its compact design, the QPRU achieves competitive forecasting performance, matching state-of-the-art baselines while offering important structural and practical advantages, including enhanced scalability and a reduced number of trainable parameters.
Machine Learning (cs.LG)
arXiv:2609.04354 [cs.LG]
(or arXiv:2609.04354v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.04354 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
2026 IEEE International Conference on Quantum Communications, Networking, and Computing (QCNC), pp. 776-780, 2026
https://doi.org/10.1109/QCNC69040.2026.00126 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 190 words
