CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter Generation
CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter Generation
复制标题
DOI：
10.1145/3583780.3614802
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Guang Yang;Yuequn Zhang;Jinquan Hang;Xinyue Feng;Zejun Xie;Desheng Zhang;Yu Yang
中科院分区：
文献类型：
--
作者：
Guang Yang;Yuequn Zhang;Jinquan Hang;Xinyue Feng;Zejun Xie;Desheng Zhang;Yu Yang
交通事故预测是公共安全、应急处理和城市管理的重要问题。现有的工作利用从城市基础设施收集的大量数据，以基于各种机器学习技术实现令人鼓舞的性能，但在数据有限的情况下无法实现良好的性能（即，数据稀缺）。迁移学习的最新发展为解决数据稀缺问题带来了新的机遇。在本文中，我们设计了一个新的跨城市迁移学习框架称为CARPG预测数据稀缺的城市中的交通事故。我们解决了预测交通事故的独特挑战，这是由其两个基本特征引起的，即，空间异质性和固有的稀缺性，这导致了最先进的迁移学习方法的偏差性能。具体来说，我们通过共同学习源城市和目标城市的空间区域表示与城市间的全球图形知识转移过程来建立跨城市区域连接。此外，我们设计了一个有效的基于注意力的参数生成机制，学习特定区域的交通事故模式，同时控制参数的总数。在此基础上，我们确保在知识转移过程中，只有相关的模式才能转移到每个目标区域，并进一步进行微调。我们在三个真实世界的数据集上进行了广泛的实验，评估结果表明，与最先进的基线模型相比，我们的框架的优越性。
Traffic accident prediction is a crucial problem for public safety, emergency treatment, and urban management. Existing works leverage extensive data collected from city infrastructures to achieve encouraging performance based on various machine learning techniques but cannot achieve a good performance in situations with limited data (i.e., data scarcity). Recent developments in transfer learning bring a new opportunity to solve the data scarcity problem. In this paper, we design a novel cross-city transfer learning framework named CARPG for predicting traffic accidents in data-scarce cities. We address the unique challenge of predicting traffic accidents caused by its two fundamental characteristics, i.e., spatial heterogeneity and inherent rareness, which result in the biased performance of the state-of-the-art transfer learning methods. Specifically, we build cross-city region connections by jointly learning the spatial region representations for both source and target cities with an inter-city global graph knowledge transfer process. Further, we design an efficient attention-based parameter-generating mechanism to learn region-specific traffic accident patterns, while controlling the total number of parameters. Built upon that, we ensure that only relevant patterns are transferred to each target region during the knowledge transfer process and further to be fine-tuned. We conduct extensive experiments on three real-world datasets, and the evaluation results demonstrate the superiority of our framework compared with state-of-the-art baseline models.