{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T00:53:27Z","timestamp":1771721607207,"version":"3.50.1"},"reference-count":76,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20222003"],"award-info":[{"award-number":["BK20222003"]}],"id":[{"id":"10.13039\/501100004608","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":[[2025,1,31]]},"abstract":"<jats:p>\n            <jats:bold>Multivariate Time Series Classification (MTSC)<\/jats:bold>\n            is a fundamental data mining task, which is widely applied in the fields like health care and energy management. However, the existing MTSC methods are mostly adapted from univariate versions and model the static patterns among series in the time domain. We argue they fail to capture the inter-dependencies across variables and rarely consider the unique dynamic features in multilevel frequencies, which are susceptible to signal noise and lack sufficient feature extraction capability to achieve satisfactory classification accuracy. To address these issues, we propose a novel framework called\n            <jats:bold>Multilevel Dynamic Wavelet Graph Neural Network (MagNet)<\/jats:bold>\n            , which effectively captures inherent temporal-frequency dependencies in multivariate time series data in a global view, facilitating the information flow among inter-related variables and leveraging learnable\n            <jats:bold>Graph Neural Networks (GNNs)<\/jats:bold>\n            to uncover dynamic frequency dependencies. We propose an orthogonal temporal convolution layer that utilizes soft orthogonal losses to constrain features learned at different frequency components to reduce feature redundancy. Additionally, we introduce a hierarchical graph coarsening operator to address the flat learning challenges in traditional GNNs. Our dynamic wavelet GNN and hierarchical coarsening enable deep model stacking and end-to-end learning. Extensive experiments on 30 UEA benchmarks demonstrate that our method outperforms the state-of-the-art baselines in the MTSC tasks.\n          <\/jats:p>","DOI":"10.1145\/3703915","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T13:50:48Z","timestamp":1731419448000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MagNet: Multilevel Dynamic Wavelet Graph Neural Network for Multivariate Time Series Classification"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8019-0075","authenticated-orcid":false,"given":"Xiaobin","family":"Hong","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2466-156X","authenticated-orcid":false,"given":"Jiangyi","family":"Hu","sequence":"additional","affiliation":[{"name":"State Grid Chongqing Electric Power Company, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0785-2157","authenticated-orcid":false,"given":"Taishan","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Technology and Equipment for Defense against Power System Operational Risks, Nari Technology Co., Ltd., Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3442-7162","authenticated-orcid":false,"given":"Xiancheng","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Technology and Equipment for Defense against Power System Operational Risks, Nari Technology Co., Ltd., Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5514-2745","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Technology and Equipment for Defense against Power System Operational Risks, Nari Technology Co., Ltd., Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0892-5161","authenticated-orcid":false,"given":"Xiangkai","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9199-3655","authenticated-orcid":false,"given":"Wenzhong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_1_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. arXiv:1811.00075. Retrieved from https:\/\/arxiv.org\/abs\/1811.00075"},{"key":"e_1_3_1_3_2","first-page":"6370","volume-title":"IEEE Transactions on Knowledge and Data Engineering","volume":"36","author":"Bai Lu","year":"2024","unstructured":"Lu Bai, Lixin Cui, Yue Wang, Ming Li, Jing Li, S. Yu Philip, and Edwin R. Hancock. 2024. HAQJSK: Hierarchical-aligned quantum Jensen-Shannon kernels for graph classification. IEEE Transactions on Knowledge and Data Engineering 36, 11 (Nov 2024), 6370\u20136384. DOI: 10.1109\/TKDE.2024.3389966"},{"key":"e_1_3_1_4_2","first-page":"374","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Balestriero Randall","year":"2018","unstructured":"Randall Balestriero and Richard G. Baraniuk. 2018. A spline theory of deep learning. In Proceedings of the International Conference on Machine Learning. PMLR, 374\u2013383."},{"key":"e_1_3_1_5_2","volume-title":"Digital Image Processing","author":"Castleman Kenneth R.","year":"1996","unstructured":"Kenneth R. Castleman. 1996. Digital Image Processing. Prentice Hall Press."},{"key":"e_1_3_1_6_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR \u201921)","author":"Chen Yuzhou","year":"2021","unstructured":"Yuzhou Chen, Ignacio Segovia-Dominguez, Baris Coskunuzer, and Yulia Gel. 2021. TAMP-S2GCNets: Coupling time-aware multipersistence knowledge representation with spatio-supra graph convolutional networks for time-series forecasting. In Proceedings of the International Conference on Learning Representations (ICLR \u201921). Retrieved https:\/\/openreview.net\/forum?id=wv6g8fWLX2q"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10905-014-9454-4"},{"key":"e_1_3_1_8_2","first-page":"829","volume-title":"Proceedings of the 2022 IEEE 39th International Conference on Data Engineering (ICDE \u201922)","author":"Chen Yuqi","year":"2022","unstructured":"Yuqi Chen, Hanyuan Zhang, Weiwei Sun, and Baihua Zheng. 2022. RNTrajRec: Road network enhanced trajectory recovery with spatial-temporal transformer. In Proceedings of the 2022 IEEE 39th International Conference on Data Engineering (ICDE \u201922), 829\u2013842. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:254017729"},{"key":"e_1_3_1_9_2","first-page":"2900","volume-title":"Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE \u201922).","author":"Cirstea Razvan-Gabriel","year":"2022","unstructured":"Razvan-Gabriel Cirstea, Bin Yang, Chenjuan Guo, Tung Kieu, and Shirui Pan. 2022. Towards spatio-temporal aware traffic time series forecasting. In Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE \u201922). IEEE, 2900\u20132913."},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1109\/JAS.2019.1911747","article-title":"The UCR time series archive","volume":"6","author":"Dau Hoang Anh","year":"2019","unstructured":"Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, and Eamonn Keogh. 2019. The UCR time series archive. IEEE\/CAA Journal of Automatica Sinica 6 (2019), 1293\u20131305.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"5","key":"e_1_3_1_11_2","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster Angus","year":"2020","unstructured":"Angus Dempster, Fran\u00e7ois Petitjean, and Geoffrey I. Webb. 2020. ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery 34, 5 (2020), 1454\u20131495.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123452"},{"key":"e_1_3_1_13_2","first-page":"517","volume-title":"Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923)","author":"Fang Yuchen","year":"2023","unstructured":"Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Liang Zeng, and Chenxing Wang. 2023. When spatio-temporal meet wavelets: Disentangled traffic forecasting via efficient spectral graph attention networks. In Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923), 517\u2013529. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:260171424"},{"key":"e_1_3_1_14_2","volume-title":"Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan E. Lenssen. 2019. Fast graph representation learning with PyTorch geometric. In Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifolds."},{"key":"e_1_3_1_15_2","first-page":"20592","article-title":"Wavelet feature maps compression for image-to-image CNNs","volume":"35","author":"Finder Shahaf E.","year":"2022","unstructured":"Shahaf E. Finder, Yair Zohav, Maor Ashkenazi, and Eran Treister. 2022. Wavelet feature maps compression for image-to-image CNNs. Advances in Neural Information Processing Systems 35 (2022), 20592\u201320606.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_16_2","article-title":"Unsupervised scalable representation learning for multivariate time series","volume":"32","author":"Franceschi Jean-Yves","year":"2019","unstructured":"Jean-Yves Franceschi, Aymeric Dieuleveut, and Martin Jaggi. 2019. Unsupervised scalable representation learning for multivariate time series. In Advances in Neural Information Processing Systems, Vol. 32.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_17_2","volume-title":"Proceedings of the 31th International Joint Conference on Artificial Intelligence (IJCAI \u201922)","author":"Gao Ge","year":"2022","unstructured":"Ge Gao, Qitong Gao, Xi Yang, Miroslav Pajic, and Min Chi. 2022. A reinforcement learning-informed pattern mining framework for multivariate time series classification. In Proceedings of the 31th International Joint Conference on Artificial Intelligence (IJCAI \u201922)."},{"key":"e_1_3_1_18_2","first-page":"151","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Guo Kan","year":"2021","unstructured":"Kan Guo, Yongli Hu, Yanfeng Sun, Sean Qian, Junbin Gao, and Baocai Yin. 2021. Hierarchical graph convolution network for traffic forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 151\u2013159."},{"key":"e_1_3_1_19_2","first-page":"1585","volume-title":"Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923)","author":"Guo S.","year":"2023","unstructured":"S. Guo, Youfang Lin, Letian Gong, Chenyu Wang, Zeyu Zhou, Zekai Shen, Yiheng Huang, and Huaiyu Wan. 2023. Self-supervised spatial-temporal bottleneck attentive network for efficient long-term traffic forecasting. In Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923), 1585\u20131596. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:260171784"},{"key":"e_1_3_1_20_2","first-page":"521","volume-title":"Proceedings of the 2010 3rd International Conference on Computer Science and Information Technology","author":"Hammami Nacereddine","year":"2010","unstructured":"Nacereddine Hammami and Mouldi Bedda. 2010. Improved tree model for Arabic speech recognition. In Proceedings of the 2010 3rd International Conference on Computer Science and Information Technology, Vol. 5, IEEE, 521\u2013526."},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/ICDM.2014.92","volume-title":"Proceedings of the 2014 IEEE International Conference on Data Mining.","author":"Hamooni Hossein","year":"2014","unstructured":"Hossein Hamooni and Abdullah Mueen. 2014. Dual-domain hierarchical classification of phonetic time series. In Proceedings of the 2014 IEEE International Conference on Data Mining. IEEE, 160\u2013169."},{"key":"e_1_3_1_22_2","first-page":"8499","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Hong Xiaobin","year":"2024","unstructured":"Xiaobin Hong, Wenzhong Li, Chaoqun Wang, Mingkai Lin, and Sanglu Lu. 2024. Label attentive distillation for GNN-based graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 8499\u20138507."},{"key":"e_1_3_1_23_2","first-page":"7711","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201921)","volume":"35","author":"Hong Xiaobin","year":"2021","unstructured":"Xiaobin Hong, Tong Zhang, Zhen Cui, Yuge Huang, Pengcheng Shen, Shaoxin Li, and Jian Yang. 2021. Graph game embedding. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201921), Vol. 35, 7711\u20137720."},{"key":"e_1_3_1_24_2","unstructured":"Keke Huang Yu Guang Wang Ming Li and Pietro Li\u00f2. 2024. How universal polynomial bases enhance spectral graph neural networks: Heterophily over-smoothing and over-squashing. arXiv:2405.12474. Retrieved from https:\/\/arxiv.org\/pdf\/2405.12474"},{"key":"e_1_3_1_25_2","first-page":"1","volume-title":"Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201923).","author":"Hussain Shehzeen","year":"2023","unstructured":"Shehzeen Hussain, Paarth Neekhara, Jocelyn Huang, Jason Li, and Boris Ginsburg. 2023. ACE-VC: Adaptive and controllable voice conversion using explicitly disentangled self-supervised speech representations. In Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201923). IEEE, 1\u20135."},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","first-page":"117921","DOI":"10.1016\/j.eswa.2022.117921","article-title":"Graph neural network for traffic forecasting: A survey","volume":"207","author":"Jiang Weiwei","year":"2022","unstructured":"Weiwei Jiang and Jiayun Luo. 2022. Graph neural network for traffic forecasting: A survey. Expert Systems with Applications 207 (2022), 117921.","journal-title":"Expert Systems with Applications"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.05.012"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Fazle Karim Somshubra Majumdar Houshang Darabi and Samuel Harford. 2019. Multivariate LSTM-FCNs for time series classification. Neural Networks 116 (2019) 237\u2013245.","DOI":"10.1016\/j.neunet.2019.04.014"},{"key":"e_1_3_1_29_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_1_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.075"},{"key":"e_1_3_1_31_2","first-page":"8375","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Li Guozhong","year":"2021","unstructured":"Guozhong Li, Byron Choi, Jianliang Xu, Sourav S. Bhowmick, Kwok-Pan Chun, and Grace Lai-Hung Wong. 2021. Shapenet: A shapelet-neural network approach for multivariate time series classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 8375\u20138383."},{"key":"e_1_3_1_32_2","first-page":"1781","volume-title":"Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE \u201922).","author":"Li Guozhong","year":"2022","unstructured":"Guozhong Li, Byron Choi, Jianliang Xu, Sourav S. Bhowmick, Daphne Ngar-yin Mah, and Grace L. H. Wong. 2022. IPS: Instance profile for shapelet discovery for time series classification. In Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE \u201922). IEEE, 1781\u20131793."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467373"},{"key":"e_1_3_1_34_2","first-page":"4367","volume-title":"IEEE Transactions on Neural Networks and Learning Systems","author":"Li Ming","year":"2024","unstructured":"Ming Li, Alessio Micheli, Yu Guang Wang, Shirui Pan, Pietro Li\u00f3, Giorgio Stefano Gnecco, and Marcello Sanguineti. 2024. Guest editorial: Deep neural networks for graphs: Theory, models, algorithms, and applications. IEEE Transactions on Neural Networks and Learning Systems 35, 4 (2024), 4367\u20134372."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16542"},{"key":"e_1_3_1_36_2","first-page":"1292","article-title":"Scalable multi-source pre-training for graph neural networks","author":"Lin Mingkai","year":"2024","unstructured":"Mingkai Lin, Wenzhong Li, Xiaobin Hong, and Sanglu Lu. 2024. Scalable multi-source pre-training for graph neural networks. In ACM Multimedia 2024, 1292\u20131301.","journal-title":"ACM Multimedia"},{"key":"e_1_3_1_37_2","first-page":"120914","article-title":"TodyNet: Temporal dynamic graph neural network for multivariate time series classification","author":"Liu Huaiyuan","year":"2024","unstructured":"Huaiyuan Liu, Xianzhang Liu, Donghua Yang, Zhiyu Liang, Hongzhi Wang, Yong Cui, and Jun Gu. 2024. TodyNet: Temporal dynamic graph neural network for multivariate time series classification. Information Sciences (2024), 120914.","journal-title":"Information Sciences"},{"key":"e_1_3_1_38_2","first-page":"887","volume-title":"Proceedings of the 2024 IEEE 40th International Conference on Data Engineering (ICDE \u201924)","author":"Ma Xiangkai","year":"2024","unstructured":"Xiangkai Ma, Xiaobin Hong, Sanglu Lu, and Wenzhong Li. 2024. TS3Net: Triple decomposition with spectrum gradient for long-term time series analysis. In Proceedings of the 2024 IEEE 40th International Conference on Data Engineering (ICDE \u201924). IEEE, 887\u2013900."},{"issue":"11","key":"e_1_3_1_39_2","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens","year":"2008","unstructured":"Laurens Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_40_2","first-page":"674","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Mallat Stephane G.","year":"1989","unstructured":"Stephane G. Mallat. 1989. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11 (1989), 674\u2013693."},{"key":"e_1_3_1_41_2","volume-title":"Proceedings of the National Academy of Sciences","volume":"119","author":"Michau Gabriel","year":"2022","unstructured":"Gabriel Michau, Gaetan Frusque, and Olga Fink. 2022. Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series. Proceedings of the National Academy of Sciences 119, 8 (2022), e2106598119."},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"e_1_3_1_43_2","first-page":"29009","article-title":"Feature programming for multivariate time series prediction","author":"Reneau Alex","year":"2023","unstructured":"Alex Reneau, Jerry Yao-Chieh Hu, Chenwei Xu, Weijian Li, Ammar Gilani, and Han Liu. 2023. Feature programming for multivariate time series prediction. In International Conference on Machine Learning. PMLR, 29009\u201329029.","journal-title":"International Conference on Machine Learning"},{"key":"e_1_3_1_44_2","unstructured":"Patrick Sch\u00e4fer and Ulf Leser. 2017. Multivariate time series classification with WEASEL \\(+\\) MUSE. arXiv:1711.11343. Retrieved from https:\/\/arxiv.org\/pdf\/1711.11343"},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1109\/SSCI.2015.199","volume-title":"Proceedings of the 2015 IEEE Symposium Series on Computational Intelligence.","author":"Seto Skyler","year":"2015","unstructured":"Skyler Seto, Wenyu Zhang, and Yichen Zhou. 2015. Multivariate time series classification using dynamic time warping template selection for human activity recognition. In Proceedings of the 2015 IEEE Symposium Series on Computational Intelligence. IEEE, 1399\u20131406."},{"key":"e_1_3_1_46_2","unstructured":"Jianheng Tang Fengrui Hua Ziqi Gao Peilin Zhao and Jia Li. 2023. GADBench: Revisiting and benchmarking supervised graph anomaly detection. In Advances in Neural Information Processing Systems Vol. 36 29628\u201329653. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/5eaafd67434a4cfb1cf829722c65f184-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_1_47_2","first-page":"21076","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Tang Jianheng","year":"2022","unstructured":"Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. 2022. Rethinking graph neural networks for anomaly detection. In Proceedings of the International Conference on Machine Learning. ICML, 21076\u201321089."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.11.060"},{"key":"e_1_3_1_49_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). Retrieved from https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"e_1_3_1_50_2","first-page":"11505","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201920)","author":"Wang Jiayun","year":"2020","unstructured":"Jiayun Wang, Yubei Chen, Rudrasis Chakraborty, and Stella X. Yu. 2020. Orthogonal convolutional neural networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201920), 11505\u201311515."},{"key":"e_1_3_1_51_2","first-page":"1","volume-title":"IEEE Transactions on Instrumentation and Measurement","author":"Wang Jing","year":"2022","unstructured":"Jing Wang, Shikuan Shao, Yunfei Bai, Jiaoxue Deng, and Youfang Lin. 2022. Multiscale wavelet graph autoencoder for multivariate time-series anomaly detection. IEEE Transactions on Instrumentation and Measurement 72 (2022), 1\u201311."},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"2437","DOI":"10.1145\/3219819.3220060","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mmining","author":"Wang Jingyuan","year":"2018","unstructured":"Jingyuan Wang, Ze Wang, Jianfeng Li, and Junjie Wu. 2018. Multilevel wavelet decomposition network for interpretable time series analysis. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mmining, 2437\u20132446."},{"key":"e_1_3_1_53_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Woo Gerald","year":"2022","unstructured":"Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, and Steven Hoi. 2022. CoST: Contrastive learning of disentangled seasonal-trend representations for time series forecasting. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=PilZY3omXV2"},{"key":"e_1_3_1_54_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, 22419\u201322430."},{"key":"e_1_3_1_55_2","unstructured":"Wenjie Xi Arnav Jain Li Zhang and Jessica Lin. 2023. LB-SimTSC: An efficient similarity-aware graph neural network for semi-supervised time series classification. arXiv:2301.04838. Retrieved from https:\/\/arxiv.org\/abs\/2301.04838"},{"key":"e_1_3_1_56_2","first-page":"992","volume-title":"Proceedings of the ACM Web Conference 2023","author":"Xia Lianghao","year":"2023","unstructured":"Lianghao Xia, Chao Huang, Chunzhen Huang, Kangyi Lin, Tao Yu, and Ben Kao. 2023. Automated self-supervised learning for recommendation. In Proceedings of the ACM Web Conference 2023, 992\u20131002."},{"key":"e_1_3_1_57_2","first-page":"6176","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR \u201917)","author":"Xie Di","year":"2017","unstructured":"Di Xie, Jiang Xiong, and Shiliang Pu. 2017. All you need is beyond a good init: Exploring better solution for training extremely deep convolutional neural networks with orthonormality and modulation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR \u201917), 6176\u20136185."},{"key":"e_1_3_1_58_2","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv:1810.00826. Retrieved from https:\/\/arxiv.org\/abs\/1810.00826"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10944-0"},{"issue":"5","key":"e_1_3_1_60_2","first-page":"3904","article-title":"How to build a graph-based deep learning architecture in traffic domain: A survey","volume":"23","author":"Ye Jiexia","year":"2020","unstructured":"Jiexia Ye, Juanjuan Zhao, Kejiang Ye, and Chengzhong Xu. 2020. How to build a graph-based deep learning architecture in traffic domain: A survey. IEEE Transactions on Intelligent Transportation Systems 23, 5 (2020), 3904\u20133924.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0179-5"},{"key":"e_1_3_1_62_2","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS \u201923)","author":"Yi Kun","year":"2023","unstructured":"Kun Yi, Qi Zhang, Wei Fan, Hui He, Liang Hu, Pengyang Wang, Ning An, Longbing Cao, and Zhendong Niu. 2023. FourierGNN: Rethinking multivariate time series forecasting from a pure graph perspective. In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS \u201923). Retrieved from https:\/\/openreview.net\/forum?id=bGs1qWQ1Fx"},{"key":"e_1_3_1_63_2","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS \u201923)","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 Conference on Neural Information Processing Systems (NeurIPS \u201923)."},{"key":"e_1_3_1_64_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_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05079-1"},{"key":"e_1_3_1_66_2","first-page":"8980","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201922)","volume":"36","author":"Yue Zhihan","year":"2022","unstructured":"Zhihan Yue, Yujing Wang, Juanyong Duan, Tianmeng Yang, Congrui Huang, Yunhai Tong, and Bixiong Xu. 2022. Ts2vec: Towards universal representation of time series. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201922), Vol. 36, 8980\u20138987."},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124591"},{"key":"e_1_3_1_69_2","first-page":"599","volume-title":"Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923)","author":"Zhang Qianzhen","year":"2023","unstructured":"Qianzhen Zhang, Deke Guo, Xiang Zhao, Long Yuan, and Lailong Luo. 2023. Discovering frequency bursting patterns in temporal graphs. In Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE \u201923), 599\u2013611. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:260172197"},{"key":"e_1_3_1_70_2","first-page":"6845","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201920)","volume":"34","author":"Zhang Xuchao","year":"2020","unstructured":"Xuchao Zhang, Yifeng Gao, Jessica Lin, and Chang-Tien Lu. 2020. Tapnet: Multivariate time series classification with attentional prototypical network. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI \u201920), Vol. 34, 6845\u20136852."},{"key":"e_1_3_1_71_2","volume-title":"Proceedings of Neural Information Processing Systems (NeurIPS \u201922)","author":"Zhang Xiang","year":"2022","unstructured":"Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis, and Marinka Zitnik. 2022. Self-supervised contrastive pre-training for time series via time-frequency consistency. In Proceedings of Neural Information Processing Systems (NeurIPS \u201922)."},{"issue":"5","key":"e_1_3_1_72_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3572780","article-title":"STAD-GAN: Unsupervised anomaly detection on multivariate time series with self-training generative adversarial networks","volume":"17","author":"Zhang Zhijie","year":"2023","unstructured":"Zhijie Zhang, Wenzhong Li, Wangxiang Ding, Linming Zhang, Qingning Lu, Peng Hu, Tong Gui, and Sanglu Lu. 2023. STAD-GAN: Unsupervised anomaly detection on multivariate time series with self-training generative adversarial networks. ACM Transactions on Knowledge Discovery from Data 17, 5 (2023), 1\u201318.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216630"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"e_1_3_1_75_2","first-page":"27168","volume-title":"Proceedings of the International Conference on Machine Learning","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 International Conference on Machine Learning, 27168\u201327286."},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1080\/00220973.1993.9943832"},{"key":"e_1_3_1_77_2","first-page":"11497","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Zuo Rundong","year":"2023","unstructured":"Rundong Zuo, Guozhong Li, Byron Choi, Sourav S. Bhowmick, Daphne Ngar-yin Mah, and Grace L. H. Wong. 2023. SVP-T: A shape-level variable-position transformer for multivariate time series classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 11497\u201311505."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703915","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:06Z","timestamp":1750295886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"references-count":76,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,31]]}},"alternative-id":["10.1145\/3703915"],"URL":"https:\/\/doi.org\/10.1145\/3703915","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"2024-05-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-31","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}