{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:35:32Z","timestamp":1777574132457,"version":"3.51.4"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Yonsei University Research Fund of 2022"},{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korean government"},{"name":"Artificial Intelligence Graduate School Program","award":["2020-0-01361"],"award-info":[{"award-number":["2020-0-01361"]}]},{"name":"Context and Activity Analysis-based Solution for Safe Childcare","award":["2021-0-00155"],"award-info":[{"award-number":["2021-0-00155"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this article, we present the method of spatio-temporal graph neural rough differential equation (STG-NRDE). Neural rough differential equations (NRDEs) are a breakthrough concept for processing time-series data. Their main concept is to use the log-signature transform to convert a time-series sample into a relatively shorter series of feature vectors. We extend the concept and design two NRDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 27 baselines. STG-NRDE shows the best accuracy in all cases, outperforming all those 27 baselines by non-trivial margins.<\/jats:p>","DOI":"10.1145\/3604808","type":"journal-article","created":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T12:10:52Z","timestamp":1686831052000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Graph Neural Rough Differential Equations for Traffic Forecasting"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6530-2662","authenticated-orcid":false,"given":"Jeongwhan","family":"Choi","sequence":"first","affiliation":[{"name":"Yonsei University, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-840X","authenticated-orcid":false,"given":"Noseong","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/274"},{"key":"e_1_3_3_3_2","first-page":"17804","volume-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems (NeurIPS\u201920)","author":"Bai Lei","year":"2020","unstructured":"Lei Bai, Lina Yao, Can Li, Xianzhi Wang, and Can Wang. 2020. Adaptive graph convolutional recurrent network for traffic forecasting. In Proceedings of the International Conference on Advances in Neural Information Processing Systems (NeurIPS\u201920). 17804\u201317815."},{"key":"e_1_3_3_4_2","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai, J. Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271 (2018).","journal-title":"arXiv:1803.01271"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1111\/tgis.12644"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.3141\/1748-12"},{"key":"e_1_3_3_7_2","series-title":"Proceedings of the 38th International Conference on Machine Learning (ICML\u201921)","first-page":"1684","volume":"139","author":"Chen Yuzhou","year":"2021","unstructured":"Yuzhou Chen, Ignacio Segovia, and Yulia R. Gel. 2021. Z-GCNETs: Time zigzags at graph convolutional networks for time series forecasting. In Proceedings of the 38th International Conference on Machine Learning (ICML\u201921)(Proceedings of Machine Learning Research, Vol. 139). PMLR, 1684\u20131694. Retrieved from https:\/\/proceedings.mlr.press\/v139\/chen21o.html."},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/en11081958"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11871"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_3_11_2","first-page":"1","article-title":"Climate modeling with neural advection\u2013diffusion equation","author":"Choi Hwangyong","year":"2023","unstructured":"Hwangyong Choi, Jeongwhan Choi, Jeehyun Hwang, Kookjin Lee, Dongeun Lee, and Noseong Park. 2023. Climate modeling with neural advection\u2013diffusion equation. Knowl. Inf. Syst. (2023), 1\u201325.","journal-title":"Knowl. Inf. Syst."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20587"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591645"},{"key":"e_1_3_3_14_2","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201923)","author":"Choi Jeongwhan","year":"2023","unstructured":"Jeongwhan Choi, Seoyoung Hong, Noseong Park, and Sung-Bae Cho. 2023. GREAD: Graph neural reaction-diffusion networks. In Proceedings of the International Conference on Machine Learning (ICML\u201923). PMLR."},{"key":"e_1_3_3_15_2","first-page":"3844","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201916)","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201916). 3844\u20133852. arXiv:1606.09375."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10985-5"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/0771-050X(80)90013-3"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467430"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1112\/plms.12013"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv14jx6sm"},{"key":"e_1_3_3_22_2","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201917)","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201917)."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280812"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.02.031"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/326"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358132"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00033"},{"key":"e_1_3_3_28_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201917)","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR\u201917)."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"e_1_3_3_30_2","series-title":"Proceedings of the 39th International Conference on Machine Learning (ICML\u201922)","first-page":"11906","volume":"162","author":"Lan Shiyong","year":"2022","unstructured":"Shiyong Lan, Yitong Ma, Weikang Huang, Wenwu Wang, Hongyu Yang, and Pyang Li. 2022. DSTAGNN: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting. In Proceedings of the 39th International Conference on Machine Learning (ICML\u201922)(Proceedings of Machine Learning Research, Vol. 162). PMLR, 11906\u201311917."},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510829"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330847"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16542"},{"key":"e_1_3_3_34_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Li Yaguang","year":"2018","unstructured":"Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In Proceedings of the International Conference on Learning Representations (ICLR\u201918). Retrieved from https:\/\/openreview.net\/forum?id=SJiHXGWAZ."},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539397"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006450"},{"key":"e_1_3_3_37_2","article-title":"Application of deep convolutional neural networks for detecting extreme weather in climate datasets","author":"Liu Yunjie","year":"2016","unstructured":"Yunjie Liu, Evan Racah, Joaquin Correa, Amir Khosrowshahi, David Lavers, Kenneth Kunkel, Michael Wehner, William Collins et\u00a0al. 2016. Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv:1605.01156 (2016).","journal-title":"arXiv:1605.01156"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488902"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470889"},{"key":"e_1_3_3_40_2","volume-title":"Differential Equations Driven by Rough Paths","author":"Lyons Terry","year":"2004","unstructured":"Terry Lyons, M. Caruana, and T. L\u00e9vy. 2004. Differential Equations Driven by Rough Paths. Springer. \u00c9cole D\u2019Et\u00e9 de Probabilit\u00e9s de Saint-Flour."},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71285-5"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.4171\/JEMS\/796"},{"key":"e_1_3_3_43_2","first-page":"7829","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201921)","author":"Morrill James","year":"2021","unstructured":"James Morrill, Cristopher Salvi, Patrick Kidger, and James Foster. 2021. Neural rough differential equations for long time series. In Proceedings of the International Conference on Machine Learning (ICML\u201921). PMLR, 7829\u20137838."},{"key":"e_1_3_3_44_2","first-page":"3405","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS\u201917)","author":"Racah Evan","year":"2017","unstructured":"Evan Racah, Christopher Beckham, Tegan Maharaj, Samira Ebrahimi Kahou, Prabhat, and Christopher Pal. 2017. Extreme weather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS\u201917). Curran Associates Inc., Red Hook, NY, 3405\u20133416."},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100178"},{"key":"e_1_3_3_46_2","first-page":"802","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201915)","author":"Shi Xingjian","year":"2015","unstructured":"Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-kin Wong, and Wang-chun Woo. 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201915). MIT Press, Cambridge, MA, 802\u2013810."},{"key":"e_1_3_3_47_2","first-page":"5622","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS\u201917)","author":"Shi Xingjian","year":"2017","unstructured":"Xingjian Shi, Zhihan Gao, Leonard Lausen, Hao Wang, Dit-Yan Yeung, Wai-kin Wong, and Wang-chun Woo. 2017. Deep learning for precipitation nowcasting: A benchmark and a new model. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS\u201917). Curran Associates Inc., Red Hook, NY, 5622\u20135632."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5438"},{"key":"e_1_3_3_49_2","first-page":"3104","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems (NeurIPS\u201914)","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems (NeurIPS\u201914). MIT Press, Cambridge, MA, 3104\u20133112."},{"key":"e_1_3_3_50_2","article-title":"Spatio-temporal weather forecasting and attention mechanism on convolutional LSTMs","author":"Tekin Selim Furkan","year":"2021","unstructured":"Selim Furkan Tekin, Oguzhan Karaahmetoglu, Fatih Ilhan, Ismail Balaban, and Suleyman Serdar Kozat. 2021. Spatio-temporal weather forecasting and attention mechanism on convolutional LSTMs. arXiv:2102.00696 (2021).","journal-title":"arXiv:2102.00696"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(97)82903-8"},{"key":"e_1_3_3_52_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations (ICLR\u201918)."},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3094332"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3169488"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"e_1_3_3_57_2","article-title":"Spatial-temporal transformer networks for traffic flow forecasting","author":"Xu Mingxing","year":"2020","unstructured":"Mingxing Xu, Wenrui Dai, Chunmiao Liu, Xing Gao, Weiyao Lin, Guo-Jun Qi, and Hongkai Xiong. 2020. Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint arXiv: Arxiv-2001.02908 (2020).","journal-title":"arXiv preprint arXiv: Arxiv-2001.02908"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2016910497"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3126830"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17761"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474837"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604808","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:05Z","timestamp":1750178765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":61,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3604808"],"URL":"https:\/\/doi.org\/10.1145\/3604808","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"2022-08-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-29","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}