面向基础时间序列模型分类任务的量子微调扩展研究
Towards Scaling Quantum Fine-Tuning of Foundational Time Series Models for Classification
浏览论文内容
中文总结 AI 辅助
该研究针对电网事件分类任务，提出wing模块扩展量子微调的带宽，使Chronos量子微调的平衡准确率提升至85.2%，为量子基础模型微调的扩展提供了模块化方案。
中文摘要 AI 辅助
时间序列基础模型可生成丰富的嵌入表示，但量子模型能否利用这些嵌入，以及混合经典-量子架构的可扩展性如何，仍不明确。为解决该问题，我们对Chronos进行微调，用于电网事件分类（PSML-5），在该模型的嵌入上添加量子头部。在汇总前按物理传感器类型对嵌入分组，已超过该基准的最佳已发表基线；在更精细的特征下，量子头部在相同输入上的平衡准确率比更大的经典多层感知器高出1.7-2.0个百分点。然而，增益会饱和：超过某一临界点后，向相同固定宽度寄存器输入更多信息不会提升性能。我们表明瓶颈既不是信息供应也不是电路表达能力，而是数据摄入带宽。为克服该限制，我们引入wing模块，这是一种独立的少量子比特电路，通过稀疏单向耦合向核心电路输入额外信息。在预注册的四种子协议下，我们将wing附加到固定12量子比特核心（使用固定特征），平衡准确率随每个添加的wing提升：无wing时为83.6%（含后选择量子比特共13量子比特），添加两个wing时达85.2%（共19量子比特）。 ablation实验证实，无新信息扩展电路无增益，而从错误样本获取信息的wing会损害准确率。这些结果重新定义了量子微调的扩展方式：新增量子比特需携带额外输入才有用，而非仅增加参数；wing为扩展带宽提供了模块化且稳定的途径。
英文摘要
Time-series foundation models produce rich embeddings, but whether quantum models can exploit them, and how far hybrid classical-quantum architectures scale, remains unclear. We address this by fine-tuning Chronos for power-grid event classification (PSML-5) with a quantum head on the model's embeddings. Grouping embeddings by physical sensor type before summarization already surpasses the best published baseline built for this benchmark, and with finer-grained features the quantum head outperforms a larger classical multilayer perceptron on identical inputs by 1.7-2.0 percentage points of balanced accuracy. Yet the gains saturate: past a point, feeding more information to the same fixed-width register yields no improvement. We show the bottleneck is neither the supply of information nor circuit expressiveness, but the bandwidth of the data intake. To overcome this limitation, we introduce the wing module, a self-contained few-qubit circuit that feeds additional information into the core circuit through a sparse, one-way coupling. Under a preregistered four-seed protocol, we attach wings to a fixed 12-qubit core with fixed features. Balanced accuracy increases with each added wing, from 83.6% with no wings (13 qubits, including a post-selection qubit) to 85.2% with two (19 qubits). Ablations establish that a circuit enlarged without new information gains nothing, while a wing fed information from the wrong sample harms accuracy. These results reframe scaling for quantum fine-tuning: added qubits help when they carry added inputs, not merely more parameters. Wings offer a modular and stable route to widening that bandwidth.
发表机构
- IonQ Inc.（IonQ公司）
- QuantumBasel（量子巴塞尔）
- Center for Quantum Computing and Quantum Coherence (QC2), Department of Physics, University of Basel（巴塞尔大学物理学院量子计算与量子相干中心）
机构由 AI 辅助整理，请以论文原文为准。
