{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:50:00Z","timestamp":1772938200311,"version":"3.50.1"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>Transportation demand forecasting is a critical precondition of optimal online transportation dispatch, which will greatly reduce drivers\u2019 wasted mileage and customers\u2019 waiting time, contributing to economic and environmental sustainability. Though various methods have been developed, the core spatio-temporal complexity remains challenging from three perspectives: (1) Compound spatial relationships. According to our empirical analysis, these relationships widely exist. Previous studies focus on capturing different spatial relationships using multi-homogeneous graphs. However, the information flow across various spatial relationships is not modeled explicitly. (2) Heterogeneity in spatial relationships. A region\u2019s neighbors under the same spatial relationship may have different weights for this region. Meanwhile, different relationships may also weigh differently. (3) Synchronicity between compound spatial relationships and temporal relationships. Previous research considers synchronous influences from spatial and temporal relationships in a homogeneous fashion while compound spatial relationships are not captured for this synchronicity.<\/jats:p>\n          <jats:p>\n            To address the aforementioned perspectives, we propose the\n            <jats:underline>S<\/jats:underline>\n            patio-\n            <jats:underline>T<\/jats:underline>\n            emporal\n            <jats:underline>H<\/jats:underline>\n            eterogeneous graph\n            <jats:underline>A<\/jats:underline>\n            ttention\n            <jats:underline>N<\/jats:underline>\n            etwork (STHAN), where the key intuition is capturing the compound spatial relationships via meta-paths explicitly. We first construct a spatio-temporal heterogeneous graph including multiple spatial relationships and temporal relationships and use meta-paths to depict compound spatial relationships. To capture the heterogeneity, we use hierarchical attention, which contains node level attention and meta-path level attention. The synchronicity between temporal relationships and spatial relationships, including compound ones, is modeled in meta-path-level attention. Our framework outperforms state-of-the-art models by reducing 6.58%, 4.57%, and 4.20% of WMAPE in experiments on three real-world datasets, respectively.\n          <\/jats:p>","DOI":"10.1145\/3565578","type":"journal-article","created":{"date-parts":[[2022,10,4]],"date-time":"2022-10-04T11:08:20Z","timestamp":1664881700000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0214-4334","authenticated-orcid":false,"given":"Shuai","family":"Ling","sequence":"first","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1068-2386","authenticated-orcid":false,"given":"Zhe","family":"Yu","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3795-8824","authenticated-orcid":false,"given":"Shaosheng","family":"Cao","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5741-2311","authenticated-orcid":false,"given":"Haipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9832-6679","authenticated-orcid":false,"given":"Simon","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Haining, China"}]}],"member":"320","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"2001","volume-title":"Proceedings of the NeurIPS","author":"Atwood James","year":"2016","unstructured":"James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Proceedings of the NeurIPS. 2001\u20132009."},{"key":"e_1_3_2_3_2","first-page":"17804","volume-title":"Proceedings of the NeurIPS","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 NeurIPS. 17804\u201317815."},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the ICLR","author":"Bruna Joan","year":"2014","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and deep locally connected networks on graphs. In Proceedings of the ICLR."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806512"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274895.3274896"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3385414"},{"key":"e_1_3_2_8_2","first-page":"3844","volume-title":"Proceedings of the NeurIPS","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 NeurIPS. 3844\u20133852."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450528"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477577"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013656"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Zhang Lingyu Geng Xu Qin Zhiwei Wang Hongjun Wang Xiao Zhang Ying Liang Jian Wu Guobin Song Xuan and Wang Yunhai. 2022. Multi-modal graph interaction for multi-graph convolution network in urban spatiotemporal forecasting. Sustainability 14 19 (2022) 12397.","DOI":"10.3390\/su141912397"},{"key":"e_1_3_2_15_2","first-page":"1263","volume-title":"Proceedings of the ICML","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural message passing for quantum chemistry. In Proceedings of the ICML. 1263\u20131272."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2016.05.019"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.001"},{"key":"e_1_3_2_18_2","first-page":"2","article-title":"Traffic forecasting via dilated temporal convolution with peak-sensitive loss","author":"Guo Ge","year":"2021","unstructured":"Ge Guo, Wei Yuan, Yisheng Lv, Wei Liu, and Jinyuan Liu. 2021. Traffic forecasting via dilated temporal convolution with peak-sensitive loss. IEEE Intelligent Transportation Systems Magazine (2021), 2\u201311.","journal-title":"IEEE Intelligent Transportation Systems Magazine"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102639"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_3_2_21_2","article-title":"Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting","author":"Guo Shengnan","year":"2021","unstructured":"Shengnan Guo, Youfang Lin, Huaiyu Wan, Xiucheng Li, and Gao Cong. 2021. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Transactions on Knowledge and Data Engineering 34, 11 (2021), 5415\u20135428.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_22_2","first-page":"1025","volume-title":"Proceedings of the NeurIPS","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the NeurIPS. 1025\u20131035."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467275"},{"key":"e_1_3_2_24_2","unstructured":"Guangyin Jin Zhexu Xi Hengyu Sha Yanghe Feng and Jincai Huang. 2020. Deep multi-view spatiotemporal virtual graph neural network for significant citywide ride-hailing demand prediction. arXiv:1701.00133. Retrieved from https:\/\/arxiv.org\/abs\/1701.00133."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103063"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2013.11.170"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12544-015-0170-8"},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of the ICLR","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 ICLR."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411894"},{"key":"e_1_3_2_30_2","article-title":"Spatio-temporal meta learning for urban traffic prediction","author":"Pan Zheyi","year":"2020","unstructured":"Zheyi Pan, Wentao Zhang, Yuxuan Liang, Weinan Zhang, Yong Yu, Junbo Zhang, and Yu Zheng. 2020. Spatio-temporal meta learning for urban traffic prediction. IEEE Transactions on Knowledge and Data Engineering 34, 3 (2020), 1462\u20131476.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411940"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16556"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00178"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5438"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3008774"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098018"},{"key":"e_1_3_2_37_2","first-page":"5998","volume-title":"Proceedings of the NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the NeurIPS. 5998\u20136008."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380186"},{"key":"e_1_3_2_41_2","volume-title":"Proceedings of the ICLR","author":"Welling Max","year":"2016","unstructured":"Max Welling and Thomas N. Kipf. 2016. Semi-supervised classification with graph convolutional networks. In Proceedings of the ICLR."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482254"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"e_1_3_2_45_2","unstructured":"Yi Xie Yun Xiong and Yangyong Zhu. 2020. ISTD-GCN: Iterative spatial-temporal diffusion graph convolutional network for traffic speed forecasting. arXiv:2008.03970. Retrieved from https:\/\/arxiv.org\/abs\/2008.03970."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59410-7_49"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00287"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414596"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11836"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330887"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.033"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3439346"},{"key":"e_1_3_2_54_2","first-page":"7354","volume-title":"Proceedings of the ICML","author":"Zhang Han","year":"2019","unstructured":"Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2019. Self-attention generative adversarial networks. In Proceedings of the ICML. 7354\u20137363."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2020.2990165"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411941"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403127"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5477"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2974494"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3565578","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3565578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:51Z","timestamp":1750182531000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3565578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3565578"],"URL":"https:\/\/doi.org\/10.1145\/3565578","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,24]]},"assertion":[{"value":"2022-04-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}