STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts
Authors: 
Binwu Wang, Jiaming Ma, Pengkun Wang, Xu Wang, Yudong Zhang, Zhengyang Zhou, Yang WangAuthors Info & Claims
Binwu Wang, Jiaming Ma, Pengkun Wang, Xu Wang, Yudong Zhang, Zhengyang Zhou, Yang WangAuthors Info & ClaimsPages 2948 - 2959
Abstract
Traffic prediction is a crucial task in the Intelligent Transportation System (ITS), receiving significant attention from both industry and academia. Numerous spatio-temporal graph convolutional networks have emerged for traffic prediction and achieved remarkable success. However, these models have limitations in terms of generalization and scalability when dealing with Out-of-Distribution (OOD) graph data with both structural and temporal shifts. To tackle the challenges of spatio-temporal shift, we propose a framework called STONE by learning invariable node dependencies, which achieve stable performance in variable environments. STONE initially employs gated-transformers to extract spatial and temporal semantic graphs. These two kinds of graphs represent spatial and temporal dependencies, respectively. Then we design three techniques to address spatio-temporal shifts. Firstly, we introduce a Fréchet embedding method that is insensitive to structural shifts, and this embedding space can integrate loose position dependencies of nodes within the graph. Secondly, we propose a graph intervention mechanism to generate multiple variant environments by perturbing two kinds of semantic graphs without any data augmentations, and STONE can explore invariant node representation from environments. Finally, we further introduce an explore-to-extrapolate risk objective to enhance the variety of generated environments. We conduct experiments on multiple traffic datasets, and the results demonstrate that our proposed model exhibits competitive performance in terms of generalization and scalability.
Supplemental Material
MP4 File - rtfp0126-video.mp4
This is a short video of paper with ID 126 which is accepted in kdd2024.
- Download
- 23.08 MB
References
[1]
Arjovsky, M., Bottou, L., Gulrajani, I., and Lopez-Paz, D. Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019).
[2]
Chen, H., Xu, Y., Huang, F., Deng, Z., Huang, W., Wang, S., He, P., and Li, Z. Label-aware graph convolutional networks. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (2020), p. 1977--1980.
[3]
Du, W., Chen, L., Wang, H., Shan, Z., Zhou, Z., Li, W., andWang, Y. Deciphering urban traffic impacts on air quality by deep learning and emission inventory. journal of environmental sciences 124 (2023), 745--757.
[4]
Du, W., Yang, X., Wu, D., Ma, F., Zhang, B., Bao, C., Huo, Y., Jiang, J., Chen, X., and Wang, Y. Fusing 2d and 3d molecular graphs as unambiguous molecular descriptors for conformational and chiral stereoisomers. Briefings in Bioinformatics 24, 1 (2023), bbac560.
[5]
Du, Y., Wang, J., Feng, W., Pan, S., Qin, T., Xu, R., and Wang, C. Adarnn: Adaptive learning and forecasting of time series. In Proceedings of the 30th ACM international conference on information & knowledge management (2021), pp. 402--411.
[6]
Hu, J., Liang, Y., Fan, Z., Chen, H., Zheng, Y., and Zimmermann, R. Graph neural processes for spatio-temporal extrapolation. arXiv preprint arXiv:2305.18719 (2023).
[7]
Huang, Q., Shen, L., Zhang, R., Cheng, J., Ding, S., Zhou, Z., and Wang, Y. Hdmixer: Hierarchical dependency with extendable patch for multivariate time series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence (2024), vol. 38, pp. 12608--12616.
[8]
Ji, J., Zhang, W., Wang, J., He, Y., and Huang, C. Self-supervised deconfounding against spatio-temporal shifts: Theory and modeling. arXiv preprint arXiv:2311.12472 (2023).
[9]
Jiang, J., Han, C., Zhao, W. X., and Wang, J. Pdformer: Propagation delayaware dynamic long-range transformer for traffic flow prediction. arXiv preprint arXiv:2301.07945 (2023).
[10]
Jin, G., Li, F., Zhang, J., Wang, M., and Huang, J. Automated dilated spatiotemporal synchronous graph modeling for traffic prediction. IEEE Transactions on Intelligent Transportation Systems (2022).
[11]
Jin, G., Liang, Y., Fang, Y., Shao, Z., Huang, J., Zhang, J., and Zheng, Y. Spatiotemporal graph neural networks for predictive learning in urban computing: A survey. IEEE Transactions on Knowledge and Data Engineering (2023).
[12]
Jin, G., Xi, Z., Sha, H., Feng, Y., and Huang, J. Deep multi-view graph-based network for city wide ride-hailing demand prediction. Neurocomputing 510 (2022), 79--94.
[13]
Jin, W., Ma, Y., Liu, X., Tang, X., Wang, S., and Tang, J. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (2020), pp. 66--74.
[14]
Jin, Y., Chen, K., and Yang, Q. Transferable graph structure learning for graphbased traffic forecasting across cities. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2023), pp. 1032--1043.
[15]
Kingma, D. P., and Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
[16]
Li, H., Wang, X., Zhang, Z., and Zhu, W. Ood-gnn: Out-of-distribution generalized graph neural network. IEEE Transactions on Knowledge and Data Engineering (2022).
[17]
Li, H., Zhao, Y., Mao, Z., Qin, Y., Xiao, Z., Feng, J., Gu, Y., Ju, W., Luo, X., and Zhang, M. A survey on graph neural networks in intelligent transportation systems. arXiv preprint arXiv:2401.00713 (2024).
[18]
Li, Z., Xia, L., Tang, J., Xu, Y., Shi, L., Xia, L., Yin, D., and Huang, C. Urbangpt: Spatio-temporal large language models. arXiv preprint arXiv:2403.00813 (2024).
[19]
Liang, Y., Ouyang, K., Wang, Y., Liu, Y., Zhang, J., Zheng, Y., and Rosenblum, D. S. Revisiting convolutional neural networks for citywide crowd flow analytics. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020, Proceedings, Part I (2021), Springer, pp. 578--594.
[20]
Liu, C., Yang, S., Xu, Q., Li, Z., Long, C., Li, Z., and Zhao, R. Spatial-temporal large language model for traffic prediction. arXiv preprint arXiv:2401.10134 (2024).
[21]
Liu, X., Xia, Y., Liang, Y., Hu, J., Wang, Y., Bai, L., Huang, C., Liu, Z., Hooi, B., and Zimmermann, R. Largest: A benchmark dataset for large-scale traffic forecasting. arXiv preprint arXiv:2306.08259 (2023).
[22]
Liu, Z., Miao, H., Zhao, Y., Liu, C., Zheng, K., and Li, H. Lighttr: A lightweight framework for federated trajectory recovery. arXiv preprint arXiv:2405.03409 (2024).
[23]
Lu, W., Wang, J., Sun, X., Chen, Y., Ji, X., Yang, Q., and Xie, X. Diversify: A general framework for time series out-of-distribution detection and generalization. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).
[24]
Ma, J., Cui, P., Kuang, K., Wang, X., and Zhu, W. Disentangled graph convolutional networks. In International conference on machine learning (2019), PMLR, pp. 4212--4221.
[25]
Miao, H., Fei, Y., Wang, S., Wang, F., and Wen, D. Deep learning based origindestination prediction via contextual information fusion. Multimedia Tools and Applications (2022), 1--17.
[26]
Miao, H., Shen, J., Cao, J., Xia, J., and Wang, S. Mba-stnet: Bayes-enhanced discriminative multi-task learning for flow prediction. TKDE (2022).
[27]
Miao, H., Zhao, Y., Guo, C., Yang, B., Kai, Z., Huang, F., Xie, J., and Jensen, C. S. A unified replay-based continuous learning framework for spatio-temporal prediction on streaming data. In ICDE (2024).
[28]
Park, H., Lee, S., Kim, S., Park, J., Jeong, J., Kim, K.-M., Ha, J.-W., and Kim, H. J. Metropolis-hastings data augmentation for graph neural networks. Advances in Neural Information Processing Systems 34 (2021), 19010--19020.
[29]
Peiravi, A., and Kheibari, H. T. A fast algorithm for connectivity graph approximation using modified manhattan distance in dynamic networks. Applied mathematics and computation 201, 1--2 (2008), 319--332.
[30]
Schölkopf, B., Locatello, F., Bauer, S., Ke, N. R., Kalchbrenner, N., Goyal, A., and Bengio, Y. Toward causal representation learning. Proceedings of the IEEE 109, 5 (2021), 612--634.
[31]
Shao, Z., Zhang, Z., Wei, W., Wang, F., Xu, Y., Cao, X., and Jensen, C. S. Decoupled dynamic spatial-temporal graph neural network for traffic forecasting. arXiv preprint arXiv:2206.09112 (2022).
[32]
Shuman, D. I., Narang, S. K., Frossard, P., Ortega, A., and Vandergheynst, P. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE signal processing magazine 30, 3 (2013), 83--98.
[33]
Song, C., Lin, Y., Guo, S., and Wan, H. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. In Proceedings of the AAAI conference on artificial intelligence (2020), vol. 34, pp. 914--921.
[34]
Wang, B., Wang, P., Zhang, Y., Wang, X., Zhou, Z., Bai, L., and Wang, Y. Towards dynamic spatial-temporal graph learning: A decoupled perspective. In Proceedings of the AAAI Conference on Artificial Intelligence (2024), vol. 38, pp. 9089--9097.
[35]
Wang, B., Wang, P., Zhang, Y., Wang, X., Zhou, Z., and Wang, Y. Conditionguided urban traffic co-prediction with multiple sparse surveillance data. IEEE Transactions on Vehicular Technology (2024).
[36]
Wang, B., Zhang, Y., Wang, P., Wang, X., Bai, L., and Wang, Y. A knowledgedriven memory system for traffic flow prediction. In International Conference on Database Systems for Advanced Applications (2023), Springer, pp. 192--207.
[37]
Wang, B., Zhang, Y., Wang, X., Wang, P., Zhou, Z., Bai, L., and Wang, Y. Pattern expansion and consolidation on evolving graphs for continual traffic prediction. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2023), pp. 2223--2232.
[38]
Wang, J., Jiang, J., Jiang, W., Han, C., and Zhao, W. X. Towards efficient and comprehensive urban spatial-temporal prediction: A unified library and performance benchmark. arXiv preprint arXiv:2304.14343 (2023).
[39]
Wang, L., Guo, D., Wu, H., Li, K., and Yu, W. Tc-gcn: Triple cross-attention and graph convolutional network for traffic forecasting. Information Fusion (2024), 102229.
[40]
Wang, S., Cao, J., Chen, H., Peng, H., and Huang, Z. Seqst-gan: Seq2seq generative adversarial nets for multi-step urban crowd flow prediction. ACM Transactions on Spatial Algorithms and Systems (TSAS) 6, 4 (2020), 1--24.
[41]
Wang, S., Miao, H., Chen, H., and Huang, Z. Multi-task adversarial spatialtemporal networks for crowd flow prediction. In CIKM (2020), pp. 1555--1564.
[42]
Wang, S., Miao, H., Li, J., and Cao, J. Spatio-temporal knowledge transfer for urban crowd flow prediction via deep attentive adaptation networks. TITS 23, 5 (2021), 4695--4705.
[43]
Wang, X., Wang, P., Wang, B., Zhang, Y., Zhou, Z., Bai, L., and Wang, Y. Latent gaussian processes based graph learning for urban traffic prediction. IEEE Transactions on Vehicular Technology (2023).
[44]
Woo, G., Liu, C., Sahoo, D., Kumar, A., and Hoi, S. Cost: Contrastive learning of disentangled seasonal-trend representations for time series forecasting. arXiv preprint arXiv:2202.01575 (2022).
[45]
Wu, Q., Zhang, H., Yan, J., and Wipf, D. Handling distribution shifts on graphs: An invariance perspective. arXiv preprint arXiv:2202.02466 (2022).
[46]
Wu, Y.-X., Wang, X., Zhang, A., He, X., and Chua, T.-S. Discovering invariant rationales for graph neural networks. arXiv preprint arXiv:2201.12872 (2022).
[47]
Wu, Z., Pan, S., Long, G., Jiang, J., and Zhang, C. Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121 (2019).
[48]
Xia, Y., Liang, Y., Wen, H., Liu, X., Wang, K., Zhou, Z., and Zimmermann, R. Deciphering spatio-temporal graph forecasting: A causal lens and treatment. arXiv preprint arXiv:2309.13378 (2023).
[49]
Yan, H., and Li, Y. A survey of generative ai for intelligent transportation systems. arXiv preprint arXiv:2312.08248 (2023).
[50]
Yang, C., Wu, Q., Wen, Q., Zhou, Z., Sun, L., and Yan, J. Towards out-ofdistribution sequential event prediction: A causal treatment. Advances in neural information processing systems 35 (2022), 22656--22670.
[51]
Yang, S., Liu, J., and Zhao, K. Space meets time: Local spacetime neural network for traffic flow forecasting. In 2021 IEEE International Conference on Data Mining (ICDM) (2021), IEEE, pp. 817--826.
[52]
Yi, J., and Park, J. Hypergraph convolutional recurrent neural network. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (2020), pp. 3366--3376.
[53]
Yu, B., Yin, H., and Zhu, Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017).
[54]
Zhang, G., Yi, J., Yuan, J., Li, Y., and Jin, D. Das: Efficient street view image sampling for urban prediction. ACM Transactions on Intelligent Systems and Technology 14, 2 (2023), 1--20.
[55]
Zhang, J., Zheng, Y., Qi, D., Li, R., and Yi, X. Dnn-based prediction model for spatio-temporal data. In Proceedings of the 24th ACM SIGSPATIAL international conference on advances in geographic information systems (2016), pp. 1--4.
[56]
Zhang, W., Zhang, L., Han, J., Liu, H., Zhou, J., Mei, Y., and Xiong, H. Irregular traffic time series forecasting based on asynchronous spatio-temporal graph convolutional network. arXiv preprint arXiv:2308.16818 (2023).
[57]
Zhang, Y., Wang, P., Wang, B., Wang, X., Zhao, Z., Zhou, Z., Bai, L., and Wang, Y. Adaptive and interactive multi-level spatio-temporal network for traffic forecasting. IEEE Transactions on Intelligent Transportation Systems (2024).
[58]
Zhao, T., Liu, Y., Neves, L., Woodford, O., Jiang, M., and Shah, N. Data augmentation for graph neural networks. In Proceedings of the aaai conference on artificial intelligence (2021), vol. 35, pp. 11015--11023.
[59]
Zhao, Z., Shen, G., Wang, L., and Kong, X. Graph spatial-temporal transformer network for traffic prediction. Big Data Research (2024), 100427.
[60]
Zheng, C., Fan, X., Wang, C., and Qi, J. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence (2020), vol. 34, pp. 1234--1241.
[61]
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence (2021), vol. 35, pp. 11106--11115.
[62]
Zhou, K., Liu, Z., Qiao, Y., Xiang, T., and Loy, C. C. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4396--4415.
[63]
Zhou, Z., Huang, Q., Wang, B., Hou, J., Yang, K., Liang, Y., and Wang, Y. Coms2t: A complementary spatiotemporal learning system for data-adaptive model evolution. arXiv preprint arXiv:2403.01738 (2024).
[64]
Zhou, Z., Huang, Q., Yang, K., Wang, K., Wang, X., Zhang, Y., Liang, Y., and Wang, Y. Maintaining the status quo: Capturing invariant relations for ood spatiotemporal learning.
[65]
Zhou, Z., Yang, K., Liang, Y., Wang, B., Chen, H., and Wang, Y. Predicting collective human mobility via countering spatiotemporal heterogeneity. IEEE Transactions on Mobile Computing (2023).
Index Terms
- STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts
Index terms have been assigned to the content through auto-classification.
Recommendations
Learning spatial-temporal feature with graph product
Highlights- Introduces a new spatial-temporal graph product convolutional framework.
- ...
AbstractEarlier works on dynamic spatial-temporal data modelling prefer using spatial-temporal factorized graph convolutional networks (GCNs), which are easy to interpret but fail to capture joint spatial-temporal correlations. Thus, lots of ...
Deep spatio-temporal 3D densenet with multiscale ConvLSTM-Resnet network for citywide traffic flow forecasting
AbstractReliable traffic flow forecasting is paramount in Intelligent Transportation Systems (ITS) as it can effectively improve traffic efficiency and social security. Its vital challenge is to effectively integrate various factors (such as ...
Learning Deep Spatio-Temporal Dependence for Semantic Video Segmentation
Semantically labeling every pixel in a video is a very challenging task as video is an information-intensive media with complex spatio-temporal dependence. We present in this paper a novel deep convolutional network architecture, called deep spatio-...
Comments
Information & Contributors
Information
Published In
August 2024
6901 pages
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 24 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- the National Natural Science Foundation of China
- the Project of Stable Support for Youth Teamin Basic Research Field, CAS
- Academic Leaders Cultivation Program, USTC
Conference
KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
August 25 - 29, 2024
Barcelona, Spain
Acceptance Rates
Overall Acceptance Rate 1,133 of 8,635 submissions, 13%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 699Total Downloads
- Downloads (Last 12 months)699
- Downloads (Last 6 weeks)77
Reflects downloads up to 02 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in