{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T13:41:46Z","timestamp":1770471706504,"version":"3.49.0"},"reference-count":69,"publisher":"Association for Computing Machinery (ACM)","issue":"8","funder":[{"name":"Innovation Methods Work Special Project","award":["2020IM020100"],"award-info":[{"award-number":["2020IM020100"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"crossref","award":["ZR2020QF112"],"award-info":[{"award-number":["ZR2020QF112"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>Multivariate time series classification (MTSC) is a significant research topic in the realm of data mining, with broad applications in different industries, including healthcare, finance, meteorology, and traffic. While existing studies have designed many classifiers based on LSTMs, CNNs, and Transformer, the sophisticated architectures raise concerns regarding efficiency in computation. Additionally, most methods concentrate on a single dimension, typically temporal patterns, without fully considering multi-dimensional information such as the independence and interactions across variables that are essential in multivariate settings. To address these challenges, this article introduces FreConvNet, a lightweight convolutional network integrated with frequency adaptive learning. Inheriting the modular design paradigm of Transformer to achieve multi-view modeling of multivariate time series. FreConvNet consists of two key components: the frequency adaptive block (FAB) and the convolutional feed-forward network (ConvFFN). The FAB leverages the Fourier Transform in conjunction with adaptive filters to capture both long-term and short-term dependencies in the temporal dimension. Following that, ConvFFN captures cross-variable and cross-feature interactions by controlling inter-channel information flow through grouped pointwise convolutions, while introducing non-linearity to enhance representational capacity. Extensive experiments conducted on the well-known UEA archive validate that FreConvNet outperforms existing convolution-based, Transformer-based, and hybrid methods in classification performance and offers a computationally efficient solution.<\/jats:p>","DOI":"10.1145\/3761818","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T16:00:46Z","timestamp":1755532846000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Convolutional Network Integrated with Frequency Adaptive Learning for Multivariate Time Series Classification"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9574-1788","authenticated-orcid":false,"given":"Yingxia","family":"Tang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3364-5492","authenticated-orcid":false,"given":"Yanxuan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4873-4567","authenticated-orcid":false,"given":"Xiangwei","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-6572","authenticated-orcid":false,"given":"Cun","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"e_1_3_2_2_2","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. arXiv:1811.00075. Retrieved from https:\/\/arxiv.org\/abs\/1811.00075"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946650"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Wei Cai Xiaomin Zhu Kaiyuan Bai Aihui Ye and Runtong Zhang. 2024. An explainable dual-mode convolutional neural network for multivariate time series classification. Knowledge-Based Systems 299 C (2024) 15 pages. DOI: 10.1016\/j.knosys.2024.112015","DOI":"10.1016\/j.knosys.2024.112015"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.178"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.073"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Mingyue Cheng Jiqian Yang Tingyue Pan Qi Liu Zhi Li and Shijin Wang. 2025. ConvTimeNet: A deep hierarchical fully convolutional model for multivariate time series analysis. In Companion Proceedings of the ACM on Web Conference 2025 (WWW\u201925). ACM 171\u2013180. DOI: 10.1145\/3701716.3715214","DOI":"10.1145\/3701716.3715214"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539329"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW60847.2023.00077"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123452"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119009"},{"key":"e_1_3_2_13_2","unstructured":"Emadeldeen Eldele Mohamed Ragab Zhenghua Chen Min Wu and Xiaoli Li. 2024. TSLANet: Rethinking transformers for time series representation learning. arXiv:2404.08472. Retrieved from https:\/\/arxiv.org\/abs\/2404.08472"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00948-2"},{"key":"e_1_3_2_15_2","unstructured":"John Guibas Morteza Mardani Zongyi Li Andrew Tao Anima Anandkumar and Bryan Catanzaro. 2022. Adaptive Fourier neural operators: Efficient token mixers for transformers. arXiv:2111.13587. Retrieved from https:\/\/arxiv.org\/abs\/2111.13587"},{"key":"e_1_3_2_16_2","unstructured":"Qi Han Zejia Fan Qi Dai Lei Sun Ming-Ming Cheng Jiaying Liu and Jingdong Wang. 2022. On the connection between local attention and dynamic depth-wise convolution. arXiv:2106.04263. Retrieved from https:\/\/arxiv.org\/abs\/2106.04263"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3694788"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3703915"},{"key":"e_1_3_2_19_2","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-024-00708-5"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109494"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2018.11.031"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.014"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0473-y"},{"key":"e_1_3_2_27_2","unstructured":"Haidar Khan and Bulent Yener. 2018. Learning filter widths of spectral decompositions with wavelets. Advances in Neural Information Processing Systems 31 (2018) 4606\u20134617. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/1a3f91fead97497b1a96d6104ad339f6-Paper.pdf"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124155"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17018"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106296"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120914"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8512761"},{"key":"e_1_3_2_34_2","unstructured":"Minghao Liu Shengqi Ren Siyuan Ma Jiahui Jiao Yizhou Chen Zhiguang Wang and Wei Song. 2021. Gated transformer networks for multivariate time series classification. arXiv:2103.14438. Retrieved from https:\/\/arxiv.org\/abs\/2103.14438"},{"key":"e_1_3_2_35_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. arXiv:1711.05101. Retrieved from https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378424"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW53433.2021.00099"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34155"},{"key":"e_1_3_2_39_2","volume-title":"11th International Conference on Learning Representations","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A time series is worth 64 words: Long-term forecasting with transformers. In Proceedings of the 11th International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=Jbdc0vTOcol"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00727-3"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0455-0"},{"key":"e_1_3_2_44_2","unstructured":"Wensi Tang Guodong Long Lu Liu Tianyi Zhou Michael Blumenstein and Jing Jiang. 2022. Omni-Scale CNNs: A simple and effective kernel size configuration for time series classification. arXiv:2002.10061. Retrieved from https:\/\/arxiv.org\/abs\/2002.10061"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102536"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","volume":"30","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 31st International Conference on Neural Information Processing Systems, Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.102227"},{"key":"e_1_3_2_49_2","unstructured":"Qingsong Wen Tian Zhou Chaoli Zhang Weiqi Chen Ziqing Ma Junchi Yan and Liang Sun. 2023. Transformers in time series: A survey. arXiv:2202.07125. Retrieved from https:\/\/arxiv.org\/abs\/2202.07125"},{"key":"e_1_3_2_50_2","volume-title":"11th International Conference on Learning Representations","author":"Wu Haixu","year":"2023","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2023. TimesNet: Temporal 2D-variation modeling for general time series analysis. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_51_2","first-page":"22419","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","volume":"34","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 22419\u201322430. Retrieved from https:\/\/dl.acm.org\/doi\/10.5555\/3540261.3541978"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06352-1"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3342640"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3370219"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119881"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832806"},{"key":"e_1_3_2_57_2","unstructured":"Kun Yi Qi Zhang Longbing Cao Shoujin Wang Guodong Long Liang Hu Hui He Zhendong Niu Wei Fan and Hui Xiong. 2023. A survey on deep learning based time series analysis with frequency transformation. arXiv:2302.02173. Retrieved from https:\/\/arxiv.org\/abs\/2302.02173"},{"key":"e_1_3_2_58_2","first-page":"24","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","volume":"36","author":"Yi Kun","year":"2023","unstructured":"Kun Yi, Qi Zhang, Wei Fan, Shoujin Wang, Pengyang Wang, Hui He, Ning An, Defu Lian, Longbing Cao, and Zhendong Niu. 2023. Frequency-domain MLPs are more effective learners in time series forecasting. In Proceedings of the 37th International Conference on Neural Information Processing Systems. A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., Article 3349, 24 pages."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110486"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.107322"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557470"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6165"},{"key":"e_1_3_2_65_2","unstructured":"Xiang Zhang Ziyuan Zhao Theodoros Tsiligkaridis and Marinka Zitnik. 2022. Self-supervised contrastive pre-training for time series via time-frequency consistency. Advances in Neural Information Processing Systems 35 (2022) 3988\u20134003. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/194b8dac525581c346e30a2cebe9a369-Paper-Conference.pdf"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"e_1_3_2_68_2","first-page":"27268","volume-title":"Proceedings of the 39th International Conference on Machine Learning, Vol","volume":"162","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In Proceedings of the 39th International Conference on Machine Learning, Vol. 162. PMLR, 27268\u201327286. Retrieved from https:\/\/proceedings.mlr.press\/v162\/zhou22g.html"},{"key":"e_1_3_2_69_2","unstructured":"Tian Zhou PeiSong Niu Xue Wang Liang Sun and Rong Jin. 2023. One fits all: Power general time series analysis by pretrained LM. arXiv:2302.11939. Retrieved from https:\/\/arxiv.org\/abs\/2302.11939"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26359"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3761818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:09:00Z","timestamp":1758301740000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3761818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":69,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3761818"],"URL":"https:\/\/doi.org\/10.1145\/3761818","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"2025-03-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}