A quantum circuit transformation (QCT) is required when executing a quantum program in a real quantum processing unit (QPU). By inserting auxiliary SWAP gates, a QCT algorithm transforms a quantum circuit to one that satisfies the connectivity constraint imposed by the QPU. Due to the nonnegligible gate error and the limited qubit coherence time of the QPU, QCT algorithms that minimize gate number or circuit depth or maximize the fidelity of output circuits are in urgent need. Unfortunately, finding optimized transformations often involve exhaustive searches, which are extremely time consuming and not practical for most circuits. In this article, we propose a framework that uses a policy artificial neural network (ANN) trained by supervised learning on shallow circuits to help existing QCT algorithms select the most promising SWAP gate. ANNs can be trained offline in a distributed way and the trained ANN can be easily incorporated into QCT algorithms to enable them to search deeper without bringing too much overhead in time complexity. Exemplary embeddings of the trained ANNs into target QCT algorithms demonstrate that the transformation performance can be consistently improved on QPUs with various connectivity structures and random or realistic quantum circuits.

中文翻译：

---

监督学习增强量子电路改造

在实际量子处理单元 (QPU) 中执行量子程序时需要进行量子电路变换 (QCT)。通过插入辅助 SWAP 门，QCT 算法将量子电路转换为满足 QPU 强加的连接约束的电路。由于QPU不可忽略的门误差和有限的量子比特相干时间，迫切需要最小化门数或电路深度或最大化输出电路保真度的QCT算法。不幸的是，找到优化的转换通常涉及详尽的搜索，这非常耗时并且对于大多数电路来说并不实用。在本文中，我们提出了一个框架，该框架使用通过浅层电路上的监督学习训练的策略人工神经网络 (ANN) 来帮助现有的 QCT 算法选择最有希望的 SWAP 门。人工神经网络可以分布式离线训练，训练后的人工神经网络可以很容易地融入到 QCT 算法中，使它们能够进行更深入的搜索，而不会带来太多时间复杂度的开销。将经过训练的 ANN 嵌入到目标 QCT 算法中的示例表明，可以在具有各种连接结构和随机或现实量子电路的 QPU 上持续改进转换性能。