[论文解读] A supervised hybrid quantum machine learning solution to the emergency escape routing problem

Nathan Haboury, Mo Kordzanganeh+7 more|arXiv (Cornell University)|Jul 28, 2023

Traffic Prediction and Management Techniques被引用 10

一句话总结

本文提出一种混合量子-经典监督学习方法，用以在不断演变的地震影响城市图上模仿逐节点的 Dijkstra 路由，相比纯经典模型具有更高的准确性，并且适用于可行的量子硬件执行。

ABSTRACT

Managing the response to natural disasters effectively can considerably mitigate their devastating impact. This work explores the potential of using supervised hybrid quantum machine learning to optimize emergency evacuation plans for cars during natural disasters. The study focuses on earthquake emergencies and models the problem as a dynamic computational graph where an earthquake damages an area of a city. The residents seek to evacuate the city by reaching the exit points where traffic congestion occurs. The situation is modeled as a shortest-path problem on an uncertain and dynamically evolving map. We propose a novel hybrid supervised learning approach and test it on hypothetical situations on a concrete city graph. This approach uses a novel quantum feature-wise linear modulation (FiLM) neural network parallel to a classical FiLM network to imitate Dijkstra's node-wise shortest path algorithm on a deterministic dynamic graph. Adding the quantum neural network in parallel increases the overall model's expressivity by splitting the dataset's harmonic and non-harmonic features between the quantum and classical components. The hybrid supervised learning agent is trained on a dataset of Dijkstra's shortest paths and can successfully learn the navigation task. The hybrid quantum network improves over the purely classical supervised learning approach by 7% in accuracy. We show that the quantum part has a significant contribution of 45.(3)% to the prediction and that the network could be executed on an ion-based quantum computer. The results demonstrate the potential of supervised hybrid quantum machine learning in improving emergency evacuation planning during natural disasters.

研究动机与目标

• 在动态地震引发的交通变化下，推动优化的应急疏散路由。
• 将路由问题建模为一个动态图，并将其重新表述为由 Dijkstra 算法引导的逐节点最短路径任务。
• 开发一种基于 FiLM 的混合架构，将经典和量子组件结合起来，以模仿最短路径决策。
• 评估量子组件在推理中的实质性贡献，并评估在离子基量子处理单元上的硬件可行性。

提出的方法

• 将疏散问题建模为一个随地震与交通效应演变的动态加权图。
• 使用 Dijkstra 算法的标注数据训练混合量子-经典监督模型，以模仿逐节点的 Dijkstra 决策。
• 使用 FiLM 神经网络对地震坐标进行调制，并使用并行的量子神经网络（PHN）处理状态特征。
• 实现一个用于地震输入的 7-qubit 变分量子电路，采用数据重新上传，以及一个用于图特征的五量子比特主电路。
• 通过一个最终的全连接层将量子和经典输出结合起来，以预测下一个节点。
• 使用到达率和准确度等指标，对比节点级 Dijkstra 的结果进行评估。

Figure 1: The mathematical abstraction of the emergency escape routing problem during an earthquake. The map of Furubira was investigated by converting it to a computational graph. Each node represents a crossroad where a decision on the direction is required. The three exit points on the map are ex

实验结果

研究问题

• RQ1 在地震期间对动态变化的城市图实现混合量子-经典模型模仿逐节点 Dijkstra 路由？
• RQ2 量子组件是否在应急路由任务的预测准确性和路径质量上有实质性贡献？
• RQ3 混合模型是否具有在当代离子基量子硬件上进行短路径决策的性能？
• RQ4 哪些输入特征与数据工程选择能在演化条件下最大化对最短路径决策的学习？

主要发现

• HQNN 实现平均准确率 94%，相较于经典神经网络的 87%。
• HQNN 实现更高的到达率，以及更多与 Dijkstra 结果同等或更快的路径。
• 量子部分在推理中有实质性贡献，在最终层的相对量子贡献为 0.45(3)。
• 该模型可在离子基量子计算机上执行以获得短路径，与仿真结果在定性方面一致。
• 混合模型对动态图变化具有鲁棒性，在某些演变环境中能够超越经典模型。

Figure 2: The supervised learning approach to the emergency escape routing problem. The hybrid quantum neural network (HQNN) trains to imitate the node-wise Dijkstra’s algorithm.