用于异常交通流预测的时空生成对抗聚类图卷积网络

doi:10.19678/j.issn.1000-3428.0070180

摘要/Abstract

摘要： 准确的交通流预测对城市交通至关重要,而交通流中的异常事件(如恶劣天气、紧急道路状况等)导致的异常交通流,对现阶段交通流模型预测的准确性提出严峻挑战。现有的交通流预测模型大多难以有效捕捉交通流数据的复杂动态模式,且计算资源开销较大。为了解决这些问题,本文提出一种用于异常交通流预测的时空生成对抗聚类图卷积网络(CG-STGAN)。构建一个基于时空生成对抗网络的模型,其中,生成器用于捕捉并模拟正常交通流数据,鉴别器则对比生成数据与原始数据,判断其是否异常。通过对抗训练,生成器和鉴别器协同提升了异常交通流的检测能力。此外,提出聚类图卷积网络,将交通图分解为多个子图,以限制图卷积的邻域扩张,从而降低内存使用并提高预测准确性。最后,结合图卷积门控循环单元挖掘交通流的短期时空特征,并通过长短期记忆(LSTM)模块学习交通流的长期依赖。实验结果表明,与基线模型相比,CG-STGAN在异常交通流预测方面表现出最佳性能。

关键词: 交通流预测, 异常交通流, 时空动态特性, 生成对抗网络, 聚类图卷积网络

Abstract: Accurate traffic flow prediction is critical for urban transportation; however, abnormal events in traffic flow, such as severe weather or emergency road conditions, present significant challenges in maintaining the accuracy of current traffic flow prediction models. Most existing models fail to accurately capture complex dynamic patterns of traffic data and often require substantial computational resources. To address these issues, this paper proposes a Spatio-Temporal Generative Adversarial Clustering Graph Convolutional Network (CG-STGAN) for abnormal traffic flow prediction. The model uses a generator to capture and simulate normal traffic flow data, while a discriminator compares the generated data with the original data to detect abnormalities. Adversarial training helps improve the ability of the model to identify abnormal traffic flows. In addition, a Cluster Graph Convolutional Network (Cluster-GCN) is introduced to divide the traffic graph into multiple subgraphs, thereby limiting graph convolution neighborhood expansion, reducing memory usage, and improving prediction accuracy. A graph convolutional gated recurrent unit is employed to extract short-term spatiotemporal features, while a Long Short-Term Memory (LSTM) module learns long-term dependencies. The results of experiments demonstrate that CG-STGAN outperforms baseline models in abnormal traffic flow prediction.

Key words: traffic flow prediction, abnormal traffic flow, spatio-temporal dynamic features, Generative Adversarial Network (GAN), Cluster Graph Convolutional Network (Cluster-GCN)

中图分类号:

TP181

张红, 杨俊译. 用于异常交通流预测的时空生成对抗聚类图卷积网络[J]. 计算机工程, 2026, 52(7): 168-178.

ZHANG Hong, YANG Junyi. Spatio-Temporal Generative Adversarial Clustered Graph Convolutional Network for Anomalous Traffic Flow Prediction[J]. Computer Engineering, 2026, 52(7): 168-178.

https://www.ecice06.com/CN/Y2026/V52/I7/168

参考文献

[1] 沈旭, 王淑营, 田媛梦, 等. 基于知识图谱和图注意力的众包任务推荐算法[J]. 计算机应用研究, 2023, 40(1): 115-121. SHEN X, WANG S Y, TIAN Y M, et al. Crowdsourced task recommendation algorithm based on knowledge graph and graph attention network[J]. Application Research of Computers, 2023, 40(1): 115-121. (in Chinese)
[2] ABHINAV K, BHATIA G K, DUBEY A, et al. TasRec: a framework for task recommendation in crowdsourcing[C]//Proceedings of the 15th International Conference on Global Software Engineering. Washington D. C., USA: IEEE Press, 2020: 86-95.
[3] LU K, WANG J X, LI M C, et al. Personalized and quality-aware task recommendation in collaborative crowdsourcing[C]//Proceedings of the IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD). Dalian, China: IEEE Press, 2021: 43-48.
[4] WANG X, WANG D X, XU C R, et al. Explainable reasoning over knowledge graphs for recommendation[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 5329-5336.
[5] HUANG Y F, ZHAO F, GUI X Y, et al. Path-enhanced explainable recommendation with knowledge graphs[J]. World Wide Web, 2021, 24(5): 1769-1789.
[6] 徐静如, 董红斌, 赵炳旭, 等. 具有角色意识的社区服务型时空众包任务分配[J]. 智能系统学报, 2023, 18(2): 293-304. XU J R, DONG H B, ZHAO B X, et al. Community service-oriented spatiotemporal crowdsourcing task allocation with role awareness[J]. CAAI Transactions on Intelligent Systems, 2023, 18(2): 293-304. (in Chinese)
[7] 孟祥福, 谢晶, 张峰. 考虑众包工人时空行为偏好的top-k任务推荐模型[J]. 小型微型计算机系统, 2023, 44(5): 974-980. MENG X F, XIE J, ZHANG F. top-k task recommendation model considering spatio-temporal behavioral preferences of crowdsourced workers[J]. Journal of Chinese Computer Systems, 2023, 44(5): 974-980. (in Chinese)
[8] ISMAILOGLU F. Aggregating user preferences in group recommender systems: a crowdsourcing approach[J]. Decision Support Systems, 2022, 152: 113663.
[9] MIAO H, ZHONG X L, LIU J X, et al. Task assignment with efficient federated preference learning in spatial crowdsourcing[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(4): 1800-1814.
[10] GAO L, GAN Y, ZHOU B H, et al. A user-knowledge crowdsourcing task assignment model and heuristic algorithm for expert knowledge recommendation systems[J]. Engineering Applications of Artificial Intelligence, 2020, 96: 103959.
[11] HUANG W Y, LI P, LI B, et al. Towards stable task assignment with preference lists and ties in spatial crowdsourcing[J]. Information Sciences, 2023, 620: 16-30.
[12] CHEN W, WAN H Y, GUO S N, et al. Building and exploiting spatial-temporal knowledge graph for next POI recommendation[J]. Knowledge-Based Systems, 2022, 258: 109951.
[13] GUO Q Y, ZHUANG F Z, QIN C, et al. A survey on knowledge graph-based recommender systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3549-3568.
[14] WANG H W, ZHANG F Z, WANG J L, et al. RippleNet: propagating user preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press, 2018: 417-426.
[15] ZHAO Y Y, WANG X, CHEN J W, et al. Time-aware path reasoning on knowledge graph for recommendation[J]. ACM Transactions on Information Systems, 2023, 41(2): 1-26.
[16] LIU J, HUANG W, LI T R, et al. Cross-domain knowledge graph chiasmal embedding for multi-domain item-item recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(5): 4621-4633.
[17] CHANG Y, ZHOU W, CAI H N, et al. Meta-relation assisted knowledge-aware coupled graph neural network for recommendation[J]. Information Processing[WT《Times New Roman》]& Management, 2023, 60(3): 103353.
[18] PHAN H T, NGUYEN N T, HWANG D. Convolutional attention neural network over graph structures for improving the performance of aspect-level sentiment analysis[J]. Information Sciences, 2022, 589: 416-439.
[19] LYU S, WANG K, WEI Y L, et al. GNN-based advanced feature integration for ICS anomaly detection[J]. ACM Transactions on Intelligent Systems and Technology, 2023, 14(6): 1-32.
[20] YANG B Y, WANG X, ZHANG S, et al. Joint modelling of task requirements and worker preferences based on heterogeneous features and multiple interactions for knowledge-intensive crowdsourcing recommendation[J]. International Journal of Bio-Inspired Computation, 2023, 22(2): 105-116.
[21] HE X N, DENG K, WANG X, et al. LightGCN: simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2020: 639-648.
[22] CHEN Z L, FU L L, YAO J, et al. Learnable graph convolutional network and feature fusion for multi-view learning[J]. Information Fusion, 2023, 95: 109-119.
[23] GAO X Y, FENG F L, HUANG H Y, et al. Food recommendation with graph convolutional network[J]. Information Sciences, 2022, 584: 170-183.
[24] WANG X, HE X N, CAO Y X, et al. KGAT: knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery[WT《Times New Roman》]& Data Mining. New York, USA: ACM Press, 2019: 950-958.
[25] REN X H, CHEN T, NGUYEN Q V H, et al. Explicit knowledge graph reasoning for conversational recommendation[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(4): 1-21.
[26] HE X N, CHUA T S. Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2017: 355-364.
[27] ZHANG F Z, YUAN N J, LIAN D F, et al. Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM Press, 2016: 353-362.
[28] WANG H W, ZHANG F Z, ZHAO M, et al. Multi-task feature learning for knowledge graph enhanced recommendation[C]//Proceedings of the World Wide Web Conference. New York, USA: ACM Press, 2019: 2000-2010.
[29] TAI C Y, WU M R, CHU Y W, et al. Mvin: learning multiview items for recommendation[C]//Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval. New York, USA: ACM Press, 2020: 99-108.
[30] WANG Z, LIN G Y, TAN H B, et al. CKAN: collaborative knowledge-aware attentive network for recommender systems[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2020: 219-228.
[31] WANG J, YAN Y P, ZHAO G S. Task recommendation method combining multimodal cognition and collaboration in mobile crowdsensing systems[J]. Computer Networks, 2023, 229: 109796.
[32] LI X L, ZHANG L C, ZHOU M, et al. Task recommendation based on user preferences and user-task matching in mobile crowdsensing[J]. Applied Intelligence, 2024, 54(1): 131-146.
[33] SHA X, SUN Z, ZHANG J. Hierarchical attentive knowledge graph embedding for personalized recommendation[J]. Electronic Commerce Research and Applications, 2021, 48: 101071.

选择文件类型/文献管理软件名称

选择包含的内容