Liu Yinghui, Shen Guojiang, Liu Nali, Han Xiao, Xu Zhenhui, Zhou Junjie, Kong Xiangjie
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China.
School of Data Science, City University of Hong Kong, Hong Kong, China.
PeerJ Comput Sci. 2024 Oct 14;10:e2408. doi: 10.7717/peerj-cs.2408. eCollection 2024.
Traffic data imputation is crucial for the reliability and efficiency of intelligent transportation systems (ITSs), forming the foundation for downstream tasks like traffic prediction and management. However, existing deep learning-based imputation methods struggle with two significant challenges: poor performance under high missing data rates and the limited incorporation of external traffic-related factors. To address these challenges, we propose a novel knowledge graph-enhanced generative adversarial network (KG-GAN) for traffic data imputation. Our approach uniquely integrates external knowledge with traffic spatiotemporal dependencies to improve data imputation quality. Specifically, we construct a fine-grained knowledge graph (KG) that differentiates attributes and relationships of external factors such as points of interest (POI) and weather conditions, facilitating more robust knowledge representation learning. We then introduce a knowledge-aware embedding cell (EM-cell) that merges traffic data with these learned external representations, providing richer inputs for the spatiotemporal GAN. Extensive experiments on a large-scale real-world traffic dataset demonstrate that KG-GAN significantly outperforms state-of-the-art methods under various missing data scenarios. Additionally, ablation studies confirm the superior performance gained from incorporating external knowledge, underscoring the importance of this approach in addressing complex missing data patterns.
交通数据插补对于智能交通系统（ITS）的可靠性和效率至关重要，是交通预测和管理等下游任务的基础。然而，现有的基于深度学习的插补方法面临两个重大挑战：在高缺失数据率下性能不佳，以及对外部交通相关因素的纳入有限。为了应对这些挑战，我们提出了一种用于交通数据插补的新型知识图谱增强生成对抗网络（KG-GAN）。我们的方法独特地将外部知识与交通时空依赖性相结合，以提高数据插补质量。具体而言，我们构建了一个细粒度知识图谱（KG），区分兴趣点（POI）和天气状况等外部因素的属性和关系，促进更强大的知识表示学习。然后，我们引入了一个知识感知嵌入单元（EM-cell），将交通数据与这些学习到的外部表示合并，为时空GAN提供更丰富的输入。在大规模真实世界交通数据集上进行的广泛实验表明，在各种缺失数据场景下，KG-GAN显著优于现有方法。此外，消融研究证实了纳入外部知识所带来的优越性能，突出了该方法在处理复杂缺失数据模式方面的重要性。
