{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:17:25Z","timestamp":1780391845393,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"Research Grants Council Collaborative Research Fund","award":["C1045-23G"],"award-info":[{"award-number":["C1045-23G"]}]},{"name":"Guangdong Provincial\/Zhuhai Key Laboratory of IRADS, Beijing Normal-Hong Kong Baptist University","award":["2022B1212010006"],"award-info":[{"award-number":["2022B1212010006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737058","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"4074-4085","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4037-4288","authenticated-orcid":false,"given":"Shuhan","family":"Zhong","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1810-7071","authenticated-orcid":false,"given":"Weipeng","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Beijing Normal-Hong Kong Baptist University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8344-830X","authenticated-orcid":false,"given":"Sizhe","family":"Song","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-9360","authenticated-orcid":false,"given":"Guanyao","family":"Li","sequence":"additional","affiliation":[{"name":"Guangzhou Urban Planning and Design Survey Research Institute, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2859-7008","authenticated-orcid":false,"given":"Zhongyi","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing Normal-Hong Kong Baptist University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4207-764X","authenticated-orcid":false,"given":"S.-H. Gary","family":"Chan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Jason Lines, Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn Keogh.","author":"Bagnall Anthony","year":"2018","unstructured":"Anthony Bagnall, Hoang Anh Dau, Jason Lines, Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn Keogh. 2018. The UEA multivariate time series classification archive, 2018. showeprint1811.00075 https:\/\/arxiv.org\/abs\/1811.00075"},{"key":"e_1_3_2_2_2_1","first-page":"21325","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Bilo\u0161 Marin","year":"2021","unstructured":"Marin Bilo\u0161, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski, and Stephan G\u00fcnnemann. 2021. Neural Flows: Efficient Alternative to Neural ODEs. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 21325-21337."},{"key":"e_1_3_2_2_3_1","unstructured":"Daniel Bolya Cheng-Yang Fu Xiaoliang Dai Peizhao Zhang Christoph Feichtenhofer and Judy Hoffman. 2022. Token merging: Your vit but faster. arXiv preprint arXiv:2210.09461(2022)."},{"key":"e_1_3_2_2_4_1","volume-title":"Recurrent neural networks for multivariate time series with missing values. Scientific reports","author":"Che Zhengping","year":"2018","unstructured":"Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. 2018. Recurrent neural networks for multivariate time series with missing values. Scientific reports, Vol. 8, 1 (2018), 6085."},{"key":"e_1_3_2_2_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chen Ricky T. Q.","year":"2018","unstructured":"Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud. 2018. Neural Ordinary Differential Equations. In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2042"},{"key":"e_1_3_2_2_7_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Brouwer Edward De","year":"2019","unstructured":"Edward De Brouwer, Jaak Simm, Adam Arany, and Yves Moreau. 2019. GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3208"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research","volume":"5946","author":"Cheng-Xian Li Steven","year":"2020","unstructured":"Steven Cheng-Xian Li and Benjamin Marlin. 2020. Learning from Irregularly-Sampled Time Series: A Missing Data Perspective. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119). PMLR, 5937-5946."},{"key":"e_1_3_2_2_12_1","first-page":"49187","volume-title":"Levine(Eds.)","volume":"36","author":"Li Zekun","year":"2023","unstructured":"Zekun Li, Shiyang Li, and Xifeng Yan. 2023. Time Series as Images: Vision Transformer for Irregularly Sampled Time Series. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine(Eds.), Vol. 36. Curran Associates, Inc., 49187-49204. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/9a17c1eb808cf012065e9db47b7ca80d-Paper-Conference.pdf"},{"key":"e_1_3_2_2_13_1","unstructured":"Youwei Liang Chongjian Ge Zhan Tong Yibing Song Jue Wang and Pengtao Xie. 2022. Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations. arxiv:2202.07800 [cs.CV]"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 1st Machine Learning for Healthcare Conference(Proceedings of Machine Learning Research","volume":"270","author":"Lipton Zachary C","year":"2016","unstructured":"Zachary C Lipton, David Kale, and Randall Wetzel. 2016. Directly Modeling Missing Data in Sequences with RNNs: Improved Classification of Clinical Time Series. In Proceedings of the 1st Machine Learning for Healthcare Conference(Proceedings of Machine Learning Research, Vol. 56). PMLR, Northeastern University, Boston, MA, USA, 253-270."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403107"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5427"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2110363.2110408"},{"key":"e_1_3_2_2_19_1","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Neil Daniel","year":"2016","unstructured":"Daniel Neil, Michael Pfeiffer, and Shih-Chii Liu. 2016. Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences. In Advances in Neural Information Processing Systems, Vol. 29. Curran Associates, Inc., Barcelona,Spain."},{"key":"e_1_3_2_2_20_1","unstructured":"Yuqi Nie Nam H. Nguyen Phanwadee Sinthong and Jayant Kalagnanam. 2023. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. arxiv:2211.14730 [cs.LG] https:\/\/arxiv.org\/abs\/2211.14730"},{"key":"e_1_3_2_2_21_1","volume-title":"High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_22_1","first-page":"5052","volume-title":"Oh(Eds.)","volume":"35","author":"Qiang Yao","year":"2022","unstructured":"Yao Qiang, Deng Pan, Chengyin Li, Xin Li, Rhongho Jang, and Dongxiao Zhu. 2022. AttCAT: Explaining Transformers via Attentive Class Activation Tokens. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh(Eds.), Vol. 35. Curran Associates, Inc., 5052-5064."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3665844.3665863"},{"key":"e_1_3_2_2_24_1","volume-title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting. arxiv:2412.10859 [cs.LG] https:\/\/arxiv.org\/abs\/2412.10859","author":"Qiu Xiangfei","year":"2025","unstructured":"Xiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo, Jilin Hu, and Bin Yang. 2025. DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting. arxiv:2412.10859 [cs.LG] https:\/\/arxiv.org\/abs\/2412.10859"},{"key":"e_1_3_2_2_25_1","volume-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems, Vol. 34 (2021), 13937-13949."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"e_1_3_2_2_27_1","volume-title":"Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge","author":"Reyna Matthew A","year":"2019","unstructured":"Matthew A Reyna, Christopher S Josef, Russell Jeter, Supreeth P Shashikumar, M Brandon Westover, Shamim Nemati, Gari D Clifford, and Ashish Sharma. 2020. Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge 2019. Critical care medicine, Vol. 48, 2 (2020), 210-217."},{"key":"e_1_3_2_2_28_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Rubanova Yulia","year":"2019","unstructured":"Yulia Rubanova, Ricky T. Q. Chen, and David K Duvenaud. 2019. Latent Ordinary Differential Equations for Irregularly-Sampled Time Series. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., Vancouver, Canada."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1076\/brhm.30.2.178.1422"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1086\/160554"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research","volume":"19405","author":"Schirmer Mona","year":"2022","unstructured":"Mona Schirmer, Mazin Eltayeb, Stefan Lessmann, and Maja Rudolph. 2022. Modeling Irregular Time Series with Continuous Recurrent Units. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 162). PMLR, 19388-19405."},{"key":"e_1_3_2_2_32_1","volume-title":"Mariano Nicolas Cruz-Bournazou, and Lars Schmidt-Thieme","author":"Scholz Randolf","year":"2023","unstructured":"Randolf Scholz, Stefan Born, Nghia Duong-Trung, Mariano Nicolas Cruz-Bournazou, and Lars Schmidt-Thieme. 2023. Latent Linear ODEs with Neural Kalman Filtering for Irregular Time Series Forecasting."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-3004(97)00087-3"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095054"},{"key":"e_1_3_2_2_35_1","volume-title":"Marlin","author":"Shukla Satya Narayan","year":"2021","unstructured":"Satya Narayan Shukla and Benjamin M. Marlin. 2021. A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series. arxiv:2012.00168 [cs.LG]"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3516367"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.046"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00183"},{"key":"e_1_3_2_2_39_1","volume-title":"Sean Bin Yang, and Bin Yang","author":"Xu Ronghui","year":"2025","unstructured":"Ronghui Xu, Hanyin Cheng, Chenjuan Guo, Hongfan Gao, Jilin Hu, Sean Bin Yang, and Bin Yang. 2025. MM-Path: Multi-modal, Multi-granularity Path Representation Learning - Extended Version. arxiv:2411.18428 [cs.LG] https:\/\/arxiv.org\/abs\/2411.18428"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220051"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17260"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29560"},{"key":"e_1_3_2_2_43_1","unstructured":"Ailing Zeng Muxi Chen Lei Zhang and Qiang Xu. 2022. Are Transformers Effective for Time Series Forecasting? arxiv:2205.13504 [cs.AI] https:\/\/arxiv.org\/abs\/2205.13504"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599543"},{"key":"e_1_3_2_2_45_1","volume-title":"Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach. In Forty-first International Conference on Machine Learning.","author":"Zhang Weijia","year":"2024","unstructured":"Weijia Zhang, Chenlong Yin, Hao Liu, Xiaofang Zhou, and Hui Xiong. 2024. Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.66"},{"key":"e_1_3_2_2_47_1","unstructured":"Xiang Zhang Marko Zeman Theodoros Tsiligkaridis and Marinka Zitnik. 2022. Graph-Guided Network for Irregularly Sampled Multivariate Time Series. arxiv:2110.05357 [cs.LG]"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3654621.3654637"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:06:21Z","timestamp":1777572381000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":48,"alternative-id":["10.1145\/3711896.3737058","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737058","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}