research-article

AutoSTL: automated spatio-temporal multi-task learning

AUTHORs:

Junbo ZhangAuthors Info & Claims

AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence

Article No.: 547, Pages 4902 - 4910

https://doi.org/10.1609/aaai.v37i4.25616

Published: 07 February 2023 Publication History

Abstract

Spatio-temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing studies fail to address this joint learning problem well, which generally solve tasks individually or a fixed task combination. The challenges lie in the tangled relation between different properties, the demand for supporting flexible combinations of tasks and the complex spatio-temporal dependency. To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly. Firstly, we propose a scalable architecture consisting of advanced spatio-temporal operations to exploit the complicated dependency. Shared modules and feature fusion mechanism are incorporated to further capture the intrinsic relationship between tasks. Furthermore, our model automatically allocates the operations and fusion weight. Extensive experiments on benchmark datasets verified that our model achieves state-of-the-art performance. As we can know, AutoSTL is the first automated spatio-temporal multi-task learning method.

References

[1]

Box, G. E.; Jenkins, G. M.; Reinsel, G. C.; and Ljung, G. M. 2015. Time series analysis: forecasting and control. John Wiley & Sons.

[2]

Caruana, R. 1997. Multitask learning. Machine learning, 28(1): 41-75.

[3]

Chen, L.; Jia, N.; Zhao, H.; Kang, Y.; Deng, J.; and Ma, S. 2022. Refined analysis and a hierarchical multi-task learning approach for loan fraud detection. Journal of Management Science and Engineering, 7(4): 589-607.

[4]

Cui, Q.; Zhang, C.; Zhang, Y.; Wang, J.; and Cai, M. 2021. ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2960-2964.

[5]

Feng, S.; Ke, J.; Yang, H.; and Ye, J. 2021. A multi-task matrix factorized graph neural network for co-prediction of zone-based and od-based ride-hailing demand. IEEE Transactions on Intelligent Transportation Systems.

[6]

Gumbel, E. J. 1954. Statistical theory of extreme values and some practical applications: a series of lectures, volume 33. US Government Printing Office.

[7]

Guo, H.; Li, X.; He, M.; Zhao, X.; Liu, G.; and Xu, G. 2016. CoSoLoRec: Joint Factor Model with Content, Social, Location for Heterogeneous Point-of-Interest Recommendation. In International Conference on Knowledge Science, Engineering and Management, 613-627. Springer.

[8]

Guo, S.; Lin, Y.; Feng, N.; Song, C.; and Wan, H. 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 33, 922-929.

[9]

Han, J.; Liu, H.; Zhu, H.; Xiong, H.; and Dou, D. 2021. Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks. In Proceedings of the 35th AAAI Conference on Artificial Intelligence.

[10]

Jang, E.; Gu, S.; and Poole, B. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144.

[11]

Li, S.; Jin, X.; Xuan, Y.; Zhou, X.; Chen, W.; Wang, Y.-X.; and Yan, X. 2019. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Advances in neural information processing systems, 32.

[12]

Li, Y.; Yu, R.; Shahabi, C.; and Liu, Y. 2018. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In International Conference on Learning Representations.

[13]

Ma, X.; Tao, Z.; Wang, Y.; Yu, H.; and Wang, Y. 2015. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 54: 187-197.

[14]

Pan, Z.; Ke, S.; Yang, X.; Liang, Y.; Yu, Y.; Zhang, J.; and Zheng, Y. 2021. AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graph*. In Proceedings of the Web Conference 2021, 1846-1855.

[15]

Shang, C.; and Chen, J. 2021. Discrete Graph Structure Learning for Forecasting Multiple Time Series. In Proceedings of International Conference on Learning Representations.

[16]

Tang, H.; Liu, J.; Zhao, M.; and Gong, X. 2020. Progressive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations. In Fourteenth ACM Conference on Recommender Systems, 269-278.

[17]

Tian, Y.; and Pan, L. 2015. Predicting short-term traffic flow by long short-term memory recurrent neural network. In 2015 IEEE international conference on smart city/Social-Com/SustainCom (SmartCity), 153-158. IEEE.

[18]

Wang, P.; Zhu, C.; Wang, X.; Zhou, Z.; Wang, G.; and Wang, Y. 2022. Inferring Intersection Traffic Patterns with Sparse Video Surveillance Information: An ST-GAN method. IEEE Transactions on Vehicular Technology.

[19]

Wang, S.; Miao, H.; Chen, H.; and Huang, Z. 2020. Multitask adversarial spatial-temporal networks for crowd flow prediction. In Proceedings of the 29th ACM international conference on information & knowledge management, 1555-1564.

[20]

Wang, Y.; Yin, H.; Chen, H.; Wo, T.; Xu, J.; and Zheng, K. 2019. Origin-destination matrix prediction via graph convolution: a new perspective of passenger demand modeling. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 1227-1235.

[21]

Wu, X.; Zhang, D.; Guo, C.; He, C.; Yang, B.; and Jensen, C. S. 2021. AutoCTS: Automated correlated time series forecasting. Proceedings of the VLDB Endowment, 15(4): 971-983.

Digital Library

[22]

Wu, Z.; Pan, S.; Long, G.; Jiang, J.; Chang, X.; and Zhang, C. 2020. Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, 753-763.

[23]

Wu, Z.; Pan, S.; Long, G.; Jiang, J.; and Zhang, C. 2019. Graph WaveNet for Deep Spatial-Temporal Graph Modeling. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, 1907-1913. International Joint Conferences on Artificial Intelligence Organization.

[24]

Xu, T.; Zhu, H.; Zhao, X.; Liu, Q.; Zhong, H.; Chen, E.; and Xiong, H. 2016. Taxi driving behavior analysis in latent vehicle-to-vehicle networks: A social influence perspective. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1285-1294. ACM.

[25]

Yao, H.; Wu, F.; Ke, J.; Tang, X.; Jia, Y.; Lu, S.; Gong, P.; Ye, J.; and Li, Z. 2018. Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 32.

[26]

Ye, J.; Sun, L.; Du, B.; Fu, Y.; and Xiong, H. 2021. Coupled layer-wise graph convolution for transportation demand prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 35, 4617-4625.

[27]

Yu, B.; Yin, H.; and Zhu, Z. 2018. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In International Joint Conferences on Artificial Intelligence Organization, 3634-3640.

[28]

Yu, F.; and Koltun, V. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122.

[29]

Zhang, C.; Zhu, F.; Wang, X.; Sun, L.; Tang, H.; and Lv, Y. 2020. Taxi demand prediction using parallel multi-task learning model. IEEE Transactions on Intelligent Transportation Systems.

[30]

Zhang, J.; Zheng, Y.; and Qi, D. 2017. Deep spatio-temporal residual networks for citywide crowd flows prediction. In Thirty-first AAAI conference on artificial intelligence.

[31]

Zhang, J.; Zheng, Y.; Qi, D.; Li, R.; and Yi, X. 2016. DNN-based prediction model for spatio-temporal data. In Proceedings of the 24th ACM SIGSPATIAL international conference on advances in geographic information systems, 14.

[32]

Zhang, J.; Zheng, Y.; Sun, J.; and Qi, D. 2019. Flow prediction in spatio-temporal networks based on multitask deep learning. IEEE Transactions on Knowledge and Data Engineering, 32(3): 468-478.

[33]

Zhao, C.; Zhao, H.; Wu, R.; Deng, Q.; Ding, Y.; Tao, J.; and Fan, C. 2022a. Multi-dimensional Prediction of Guild Health in Online Games: A Stability-Aware Multitask Learning Approach.

[34]

Zhao, X.; Fan, W.; Liu, H.; and Tang, J. 2022b. Multi-type Urban Crime Prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 4388-4396.

[35]

Zhao, X.; Liu, H.; Fan, W.; Liu, H.; Tang, J.; and Wang, C. 2021a. Autoloss: Automated loss function search in recommendations. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3959-3967.

[36]

Zhao, X.; Liu, H.; Liu, H.; Tang, J.; Guo, W.; Shi, J.; Wang, S.; Gao, H.; and Long, B. 2021b. Autodim: Field-aware embedding dimension searchin recommender systems. In Proceedings of the Web Conference 2021, 3015-3022.

[37]

Zhao, X.; and Tang, J. 2017a. Exploring Transfer Learning for Crime Prediction. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW), 1158-1159. IEEE.

[38]

Zhao, X.; and Tang, J. 2017b. Modeling Temporal-Spatial Correlations for Crime Prediction. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 497-506. ACM.

[39]

Zhou, H.; Zhang, S.; Peng, J.; Zhang, S.; Li, J.; Xiong, H.; and Zhang, W. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 11106-11115.

[40]

Zhou, Z.; Wang, Y.; Xie, X.; Chen, L.; and Liu, H. 2020. RiskOracle: a minute-level citywide traffic accident forecasting framework. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 1258-1265.

Cited By

Wang YSerra ESpezzano F(2024)Multi-Granularity Modeling in Recommendation: from the Multi-Scenario PerspectiveProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680264(5491-5494)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3680264
Li XZhao XWang ZDuan YZhang YXing CHui Yang GWang HHan SHauff CZuccon GZhang Y(2024)Optimal Transport Enhanced Cross-City Site RecommendationProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657757(1441-1451)Online publication date: 10-Jul-2024
https://dl.acm.org/doi/10.1145/3626772.3657757
Zhang ZZhao XLiu QZhang CMa QWang WZhao HWang YLiu ZFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute PredictionProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615016(3195-3205)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615016
Show More Cited By

Recommendations

True motion-compensated de-interlacing algorithm

This paper presents a true motion-compensated de-interlacing (TMCD) algorithm based on a fast true motion estimation scheme. The fast true motion estimation scheme, designated as a variable block size true motion estimation for a translated motion model ...
A Factorization-Based Approach for Articulated Nonrigid Shape, Motion and Kinematic Chain Recovery From Video

Recovering articulated shape and motion, especially human body motion, from video is a challenging problem with a wide range of applications in medical study, sport analysis and animation, etc. Previous work on articulated motion recovery generally ...
A Regularization Approach to Learning Task Relationships in Multitask Learning

Multitask learning is a learning paradigm that seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this article, we propose a regularization approach to learning the relationships between ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence

February 2023

16496 pages

ISBN:978-1-57735-880-0

Copyright © 2023 Association for the Advancement of Artificial Intelligence.

Sponsors

Association for the Advancement of Artificial Intelligence

Publisher

AAAI Press

Publication History

Published: 07 February 2023

Qualifiers

Research-article
Research
Refereed limited

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 13 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wang YSerra ESpezzano F(2024)Multi-Granularity Modeling in Recommendation: from the Multi-Scenario PerspectiveProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680264(5491-5494)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3680264
Li XZhao XWang ZDuan YZhang YXing CHui Yang GWang HHan SHauff CZuccon GZhang Y(2024)Optimal Transport Enhanced Cross-City Site RecommendationProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657757(1441-1451)Online publication date: 10-Jul-2024
https://dl.acm.org/doi/10.1145/3626772.3657757
Zhang ZZhao XLiu QZhang CMa QWang WZhao HWang YLiu ZFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute PredictionProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615016(3195-3205)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615016
Zhang ZHuang ZHu ZZhao XWang WLiu ZZhang JQin SZhao HFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)MLPST: MLP is All You Need for Spatio-Temporal PredictionProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614969(3381-3390)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614969
Ma QZhang ZZhao XLi HZhao HWang YLiu ZWang WFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic ForecastingProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614910(1756-1765)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614910

View Options

View options

Media

Figures

Other

Tables

View Table of Contents