Smart City Gnosys
Smart city article details
| Title | Muse-Net: Disentangling Multi-Periodicity For Traffic Flow Forecasting |
|---|---|
| ID_Doc | 38739 |
| Authors | Qin J.; Jia Y.; Tong Y.; Chai H.; Ding Y.; Wang X.; Fang B.; Liao Q. |
| Year | 2024 |
| Published | Proceedings - International Conference on Data Engineering |
| DOI | http://dx.doi.org/10.1109/ICDE60146.2024.00103 |
| Abstract | Accurate forecasting of traffic flow plays a crucial role in building smart cities in the new era. Previous work has achieved success in learning inherent spatial and temporal patterns of traffic flow. However, existing works investigated the multiple periodicities (e.g., hourly, daily, and weekly) of traffic via entanglement learning, which has not yet dealt with distribution shift and interaction shift problems in traffic flow. In this paper, we propose a novel disentanglement learning network, called MUSE-Net, to tackle the limitations of entanglement learning by simultaneously factorizing the exclusiveness and interaction of multi-periodic patterns in traffic flow. Grounded in the theory of mutual information, we first learn and dis-entangle exclusive and interactive representations of traffics from multi-periodic patterns. Then, we utilize semantic-pushing and semantic-pulling regularizations to encourage the learned representations to be independent and informative. Moreover, we derive a lower bound estimator to tractably optimize the disentanglement problem with multiple variables and propose a joint training model for traffic forecasting. Extensive experimental results on several real-world traffic datasets demonstrate the effectiveness of the proposed framework. The code is available at: https://github.com/JianyangQin/MUSE-Net. © 2024 IEEE. |
| Author Keywords | Disentanglement; Multi-variate; Time Series; Traffic Flow Forecasting |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
58580  | 0.873 | Lai P.; Li C.; Wang Z.; Wang C.; Liao D. | Traffic Flow Prediction Based On Graph Prompt-Finetuning; [基于图提示微调的交通流量预测] | Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 61, 8 (2024) |
| 4883 | 0.869 | Cao S.; Wu L.; Wu J.; Wu D.; Li Q. | A Spatio-Temporal Sequence-To-Sequence Network For Traffic Flow Prediction | Information Sciences, 610 (2022) |
| 44042 | 0.866 | Gou X.; Han P.; Zhang X. | Quognn: Quotient Graph Neural Network For Urban Flow Forecasting | Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 (2022) |
| 46173 | 0.862 | Ma Q.; Zhang Z.; Zhao X.; Li H.; Zhao H.; Wang Y.; Liu Z.; Wang W. | Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting | International Conference on Information and Knowledge Management, Proceedings (2023) |
| 6377 | 0.862 | Zheng Y.; Wu J.; Cai Z.; Wang S.; Wang J. | Adatm: Fine-Grained Urban Flow Inference With Adaptive Knowledge Transfer Across Multiple Cities | International Conference on Information and Knowledge Management, Proceedings (2024) |
| 47493 | 0.861 | Yang S.; Wu Q. | Sdsinet: A Spatiotemporal Dual-Scale Interaction Network For Traffic Prediction | Applied Soft Computing, 173 (2025) |
| 38415 | 0.859 | Zhao W.; Zhang S.; Zhou B.; Wang B. | Multi-Spatio-Temporal Fusion Graph Recurrent Network For Traffic Forecasting | Engineering Applications of Artificial Intelligence, 124 (2023) |
| 19929 | 0.859 | Xu X.; Wei Y.; Wang P.; Luo X.; Zhou F.; Trajcevski G. | Diffusion Probabilistic Modeling For Fine-Grained Urban Traffic Flow Inference With Relaxed Structural Constraint | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (2023) |
| 21408 | 0.859 | Zhang H.; Xie Q.; Shou Z.; Gao Y. | Dynamic Spatial-Temporal Memory Augmentation Network For Traffic Prediction | Sensors, 24, 20 (2024) |
| 36944 | 0.858 | Tian R.; Wang C.; Hu J.; Ma Z. | Mfstgn: A Multi-Scale Spatial-Temporal Fusion Graph Network For Traffic Prediction | Applied Intelligence, 53, 19 (2023) |