QMoE: A Quantum Mixture of Experts Framework for Scalable Quantum Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908438179610624 |
|---|---|
| author | Nguyen, Hoang-Quan Nguyen, Xuan-Bac Pandey, Sankalp Khan, Samee U. Safro, Ilya Luu, Khoa |
| author_facet | Nguyen, Hoang-Quan Nguyen, Xuan-Bac Pandey, Sankalp Khan, Samee U. Safro, Ilya Luu, Khoa |
| contents | Quantum machine learning (QML) has emerged as a promising direction in the noisy intermediate-scale quantum (NISQ) era, offering computational and memory advantages by harnessing superposition and entanglement. However, QML models often face challenges in scalability and expressiveness due to hardware constraints. In this paper, we propose quantum mixture of experts (QMoE), a novel quantum architecture that integrates the mixture of experts (MoE) paradigm into the QML setting. QMoE comprises multiple parameterized quantum circuits serving as expert models, along with a learnable quantum routing mechanism that selects and aggregates specialized quantum experts per input. The empirical results from the proposed QMoE on quantum classification tasks demonstrate that it consistently outperforms standard quantum neural networks, highlighting its effectiveness in learning complex data patterns. Our work paves the way for scalable and interpretable quantum learning frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05190 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QMoE: A Quantum Mixture of Experts Framework for Scalable Quantum Neural Networks Nguyen, Hoang-Quan Nguyen, Xuan-Bac Pandey, Sankalp Khan, Samee U. Safro, Ilya Luu, Khoa Quantum Physics Computer Vision and Pattern Recognition Quantum machine learning (QML) has emerged as a promising direction in the noisy intermediate-scale quantum (NISQ) era, offering computational and memory advantages by harnessing superposition and entanglement. However, QML models often face challenges in scalability and expressiveness due to hardware constraints. In this paper, we propose quantum mixture of experts (QMoE), a novel quantum architecture that integrates the mixture of experts (MoE) paradigm into the QML setting. QMoE comprises multiple parameterized quantum circuits serving as expert models, along with a learnable quantum routing mechanism that selects and aggregates specialized quantum experts per input. The empirical results from the proposed QMoE on quantum classification tasks demonstrate that it consistently outperforms standard quantum neural networks, highlighting its effectiveness in learning complex data patterns. Our work paves the way for scalable and interpretable quantum learning frameworks. |
| title | QMoE: A Quantum Mixture of Experts Framework for Scalable Quantum Neural Networks |
| topic | Quantum Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05190 |