Quantum Gated Recurrent Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2493-2504
DOI: 10.1109/tpami.2024.3519605 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Yanan Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Natural Science Foundation of Shandong Province of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
The exploration of quantum advantages with Quantum Neural Networks (QNNs) is an exciting endeavor. Recurrent neural networks, the widely used framework in deep learning, suffer from the gradient vanishing and exploding problem, which limits their ability to learn long-term dependencies. To address this challenge, in this work, we develop the sequential model of Quantum Gated Recurrent Neural Networks (QGRNNs). This model naturally integrates the gating mechanism into the framework of the variational ansatz circuit of QNNs, enabling efficient execution on near-term quantum devices. We present rigorous proof that QGRNNs can preserve the gradient norm of long-term interactions throughout the recurrent network, enabling efficient learning of long-term dependencies. Meanwhile, the architectural features of QGRNNs can effectively mitigate the barren plateau phenomenon. The effectiveness of QGRNNs in sequential learning is convincingly demonstrated through various typical tasks, including solving the adding problem, learning gene regulatory networks, and predicting stock prices. The hardware-efficient architecture and superior performance of our QGRNNs indicate their promising potential for finding quantum advantageous applications in the near term.
Förderung
- Natural Science Foundation of Shandong Province of China
- National Natural Science Foundation of China
Zitieren
APA
Li, Y., Wang, Z., Xing, R., Changheng, S., Shi, S., Li, J., Zhong, G., & Gu, Y. (2025). Quantum Gated Recurrent Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2493-2504. https://doi.org/10.1109/tpami.2024.3519605
Vancouver
Li Y, Wang Z, Xing R, Changheng S, Shi S, Li J, et al. Quantum Gated Recurrent Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2493-2504. doi:10.1109/tpami.2024.3519605
BibTeX
@article{Li2025,
author = {Li, Yanan and Wang, Zhimin and Xing, Ruipeng and Changheng, Shao and Shi, Shangshang and Li, Jiaxin and Zhong, Guoqiang and Gu, Yongjian},
title = {Quantum Gated Recurrent Neural Networks},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {4},
pages = {2493--2504},
doi = {10.1109/tpami.2024.3519605}
}
EUVIMED