Soft-MoQE:用固定量子电路路由替代变分训练的混合量子-经典架构
Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning
搞量子机器学习的朋友可以看看这篇:它直接砍掉了变分量子训练,改用经典门控网络去路由固定的量子电路嵌入,在 MNIST 和 FashionMNIST 上跑出了接近可训练 QNN 的成绩,训练成本还低好几个数量级,思路挺实用的。
来自 arXiv 2611.24798 的一篇论文提出 Soft-MoQE(Soft Mixture of Quantum Experts),用输入相关的固定量子特征映射选择与组合,取代可训练变分量子电路的训练过程。架构由一组不可训练的异构量子电路组成嵌入池,配合一个经典门控网络,逐数据点学习如何加权这些量子嵌入。
作者在三个 PCA 降维任务上做了基准测试:MNIST parity、MNIST 10 分类和 FashionMNIST。Soft-MoQE 优于单一最佳专家、所有专家的均匀平均和线性基线,性能达到与可训练量子神经网络相当的水平,全程不优化任何量子参数,量子侧训练成本降低数个数量级。
论文还分析了按类别的专家使用情况,显示学习到的路由对每个输入只组合少数几个专家,且选择依赖类别。对于受噪声、硬件资源限制和 barren plateaus 困扰的近期 QML 研究者,这提供了一条绕开变分量子训练的可行设计思路。
Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning
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.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括:Soft-MoQE、量子机器学习、Mixture of Experts、变分量子电路,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Valeria Repetto, Romina D'Aurizio, Piero Farinelli),经 AITOP 多维评分管线结构化提炼。