{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T05:05:06Z","timestamp":1778389506006,"version":"3.51.4"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>\n            Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for\n            <jats:bold>Intelligent Transportation System (ITS)<\/jats:bold>\n            . However, existing imputation methods generally perform\n            <jats:italic toggle=\"yes\">zero<\/jats:italic>\n            pre-filling techniques to initialize missing values, introducing inevitable noise. Moreover, we observe prevalent over-smoothed interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose\n            <jats:bold>Mask-Aware Graph Imputation Network (MagiNet)<\/jats:bold>\n            . Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothed imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE under\n            <jats:bold>Missing Completely at Random (MCAR)<\/jats:bold>\n            pattern. Code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/JeremyChou28\/MagiNet\">https:\/\/github.com\/JeremyChou28\/MagiNet<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3743141","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T11:53:12Z","timestamp":1749210792000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7161-2029","authenticated-orcid":false,"given":"Jianping","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6452-7029","authenticated-orcid":false,"given":"Bin","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6207-5460","authenticated-orcid":false,"given":"Zhanyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5016-9602","authenticated-orcid":false,"given":"Siyu","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4675-2032","authenticated-orcid":false,"given":"Xuejun","family":"Feng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3735-1635","authenticated-orcid":false,"given":"Hua","family":"Wei","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9033-1652","authenticated-orcid":false,"given":"Guanjie","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0357-8356","authenticated-orcid":false,"given":"Xinbing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3331-2302","authenticated-orcid":false,"given":"Chenghu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Geographical Science and Natural Resources Research, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Andrea Cini","year":"2022","unstructured":"Cini Andrea, Marisca Ivan, and Cesare Alippi. 2022. Filling the gaps: Multivariate time series imputation by graph neural networks. In International Conference on Learning Representations, 1\u201320."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.125"},{"key":"e_1_3_1_4_2","first-page":"31","article-title":"Brits: Bidirectional recurrent imputation for time series","author":"Cao Wei","year":"2018","unstructured":"Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. 2018. Brits: Bidirectional recurrent imputation for time series. In Advances in Neural Information Processing Systems, Vol. 31.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20612"},{"key":"e_1_3_1_6_2","unstructured":"Wei Fan Shun Zheng Xiaohan Yi Wei Cao Yanjie Fu Jiang Bian and Tie-Yan Liu. 2022. DEPTS: Deep expansion learning for periodic time series forecasting. arXiv:2203.07681. Retrieved from https:\/\/arxiv.org\/abs\/2203.07681"},{"issue":"1","key":"e_1_3_1_7_2","first-page":"686","article-title":"Missing value imputation for multi-view urban statistical data via spatial correlation learning","volume":"35","author":"Gong Yongshun","year":"2021","unstructured":"Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Yilong Yin, and Yu Zheng. 2021. Missing value imputation for multi-view urban statistical data via spatial correlation learning. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2021), 686\u2013698.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_1_9_2","first-page":"30","article-title":"Inductive representation learning on large graphs","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467275"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3230846"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107114"},{"key":"e_1_3_1_13_2","first-page":"31","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"Kingma Durk P.","year":"2018","unstructured":"Durk P. Kingma and Prafulla Dhariwal. 2018. Glow: Generative flow with invertible 1x1 convolutions. In Advances in Neural Information Processing Systems, Vol. 31.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_14_2","unstructured":"Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv:1312.6114. Retrieved from https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.269"},{"key":"e_1_3_1_16_2","first-page":"11906","volume-title":"International Conference on Machine Learning","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 International Conference on Machine Learning. PMLR, 11906\u201311917."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00096"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615068"},{"key":"e_1_3_1_19_2","unstructured":"Steven Cheng-Xian Li Bo Jiang and Benjamin Marlin. 2019. Misgan: Learning from incomplete data with generative adversarial networks. arXiv:1902.09599. Retrieved from https:\/\/arxiv.org\/abs\/1902.09599"},{"key":"e_1_3_1_20_2","unstructured":"Yaguang Li Rose Yu Cyrus Shahabi and Yan Liu. 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv:1707.01926. Retrieved from https:\/\/arxiv.org\/abs\/1707.01926"},{"key":"e_1_3_1_21_2","volume-title":"Statistical Analysis with Missing Data","author":"Little Roderick J. A.","year":"2019","unstructured":"Roderick J. A. Little and Donald B. Rubin. 2019. Statistical Analysis with Missing Data, Vol. 793. John Wiley & Sons."},{"key":"e_1_3_1_22_2","unstructured":"Mingzhe Liu Han Huang Hao Feng Leilei Sun Bowen Du and Yanjie Fu. 2023. PriSTI: A conditional diffusion framework for spatiotemporal imputation. arXiv:2302.09746. Retrieved from https:\/\/arxiv.org\/abs\/2302.09746"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411894"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539281"},{"key":"e_1_3_1_25_2","first-page":"4413","volume-title":"International Conference on Machine Learning","author":"Mattei Pierre-Alexandre","year":"2019","unstructured":"Pierre-Alexandre Mattei and Jes Frellsen. 2019. MIWAE: Deep generative modelling and imputation of incomplete data sets. In International Conference on Machine Learning. PMLR, 4413\u20134423."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00045"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sapharm.2021.03.009"},{"key":"e_1_3_1_28_2","first-page":"7130","volume-title":"International Conference on Machine Learning","author":"Muzellec Boris","year":"2020","unstructured":"Boris Muzellec, Julie Josse, Claire Boyer, and Marco Cuturi. 2020. Missing data imputation using optimal transport. In International Conference on Machine Learning. PMLR, 7130\u20137140."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467424"},{"key":"e_1_3_1_30_2","first-page":"512","volume-title":"IEEE Transactions on Intelligent Transportation Systems","volume":"10","author":"Qu Li","year":"2009","unstructured":"Li Qu, Li Li, Yi Zhang, and Jianming Hu. 2009. PPCA-based missing data imputation for traffic flow volume: A systematical approach. IEEE Transactions on Intelligent Transportation Systems 10, 3 (2009), 512\u2013522."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01421"},{"key":"e_1_3_1_32_2","unstructured":"Alex Rubinsteyn and Sergey Feldman. 2016. fancyimpute: An Imputation Library for Python. Retrieved from https:\/\/github.com\/iskandr\/fancyimpute"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925479"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539396"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551827"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783317"},{"key":"e_1_3_1_38_2","first-page":"30","article-title":"Attention is all you need","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 Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3233890"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3531504"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.10.097"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380186"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3080546.3080549"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4067"},{"key":"e_1_3_1_45_2","unstructured":"Zonghan Wu Shirui Pan Guodong Long Jing Jiang and Chengqi Zhang. 2019. Graph wavenet for deep spatial-temporal graph modeling. arXiv:1906.00121. Retrieved from https:\/\/arxiv.org\/abs\/1906.00121"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3119638"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00929"},{"key":"e_1_3_1_48_2","first-page":"55115","article-title":"Filternet: Harnessing frequency filters for time series forecasting","volume":"37","author":"Yi Kun","year":"2024","unstructured":"Kun Yi, Jingru Fei, Qi Zhang, Hui He, Shufeng Hao, Defu Lian, and Wei Fan. 2024. Filternet: Harnessing frequency filters for time series forecasting. In Advances in Neural Information Processing Systems, Vol. 37, 55115\u201355140.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357822"},{"key":"e_1_3_1_50_2","first-page":"5689","volume-title":"International Conference on Machine Learning","author":"Yoon Jinsung","year":"2018","unstructured":"Jinsung Yoon, James Jordon, and Mihaela Schaar. 2018. Gain: Missing data imputation using generative adversarial nets. In International Conference on Machine Learning. PMLR, 5689\u20135698."},{"key":"e_1_3_1_51_2","unstructured":"Bing Yu Haoteng Yin and Zhanxing Zhu. 2017. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv:1709.04875. Retrieved from https:\/\/arxiv.org\/abs\/1709.04875"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403127"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983357"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679532"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T21:46:15Z","timestamp":1754603175000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":53,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3743141"],"URL":"https:\/\/doi.org\/10.1145\/3743141","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"assertion":[{"value":"2024-06-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}