基于混合态原型的量子增量学习

中文摘要 AI 辅助

增量学习模型需要在参数和内存约束下，按顺序学习新类别且避免灾难性遗忘。在有噪声的中等规模量子（NISQ）时代，尽管量子神经网络在特征映射上具有优势，但硬件限制了电路宽度；此外，传统量子分类器受正交基态数量限制，难以容纳持续增长的类别数量。因此，我们提出一种基于可训练混合态原型的新型量子增量学习框架，其核心设计是通过添加类别原型而非增加共享量子主干的电路宽度来纳入新类别。混合态原型的使用是另一关键贡献，因为其表征能力优于单个纯态原型，且可分解的混合态计算成本更低，还能提供便捷的希尔伯特-施密特（HS）距离度量用于分类。仿真结果表明，我们的模型用最少的量子比特实现了高维特征集中，在增量学习任务中相比经典基线展现出更低的计算复杂度和鲁棒的表征能力。

英文摘要

Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Intermediate-Scale Quantum (NISQ) era, although quantum neural networks offer advantages in feature mapping, hardware limitations restrict circuit width. Furthermore, traditional quantum classifiers are constrained by the number of orthogonal basis states, limiting their capacity to accommodate a continually growing number of categories. Thus, we introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes. Its original design incorporates new classes by adding class prototypes rather than increasing the circuit width of the shared quantum backbone. The use of mixed-state prototypes is another key contribution, since they have representation capabilities to represent information than a single pure-state prototype. And the decomposable mixed-state calculation provides lower production costs and a convenient Hilbert-Schmidt (HS) distance metric for classification. Simulation results show that our model achieves high-dimensional feature concentration using a minimal number of qubits, while demonstrating lower computational complexity and robust representation in incremental learning tasks compared with classical baselines.

发表机构

• Northwestern Polytechnical University（西北工业大学）
• Nanyang Technological University（南洋理工大学）
• University of Alberta（阿尔伯塔大学）
• Macau University of Science and Technology（澳门科技大学）
• Polish Academy of Sciences（波兰科学院）
• Istinye University（伊斯蒂涅大学）

机构由 AI 辅助整理，请以论文原文为准。