arXiv cs.AI· Valeria Repetto, Romina D'Aurizio, Piero Farinelli·· 10 小时前AI 评分20
Soft-MoQE:用固定量子特征图混合实现混合量子-经典学习
Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning
AI 导读
研究者提出 Soft-MoQE,一种软混合量子专家架构,用输入相关的固定量子特征图选择与组合替代变分量子训练,由经典门控网络为每个数据点学习各嵌入的权重。
正文 · 原文
Abstract:Quantum Machine Learning (QML) has attracted increasing interest as a possible route to construct feature representations that are difficult to reproduce with classical models. However, near-term QML architectures based on trainable parametrized quantum circuits remain affected by limited hardware resources, noise, and severe optimization difficulties such as barren plateaus. In this work we propose Soft-MoQE, a Soft Mixture of Quantum Experts architecture that replaces variational quantum training with the input-dependent selection and combination of fixed quantum feature maps. The model is composed of a heterogeneous pool of non-trainable quantum circuits, each defining a distinct embedding, and a classical gating network that learns how to weight these embeddings for each data point. We benchmark Soft-MoQE on three PCA-reduced tasks: MNIST parity, MNIST 10-class, and FashionMNIST. Soft-MoQE outperforms the single best expert, the uniform average of all experts and a linear baseline, achieving task-dependent performance comparable to that of a trainable quantum neural network, without optimizing any quantum parameter and with a quantum training cost that is lower by orders of magnitude. The analysis of the class- conditioned expert usage shows that the learned routing combines a few experts for each input, with a selection that depends on the class. These results support the learned routing among fixed quantum circuits as a trainability-aware design principle for hybrid QML.
| Comments: | 15,pages, 6 figures |
| Subjects: | Quantum Physics (quant-ph); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24798 [quant-ph] |
| (or arXiv:2611.24798v1 [quant-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24798 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Valeria Repetto [view email]
[v1]
Wed, 18 Nov 2026 17:41:45 UTC (2,689 KB)
来源:arXiv cs.AI · arxiv.org