{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:09:58Z","timestamp":1776442198622,"version":"3.51.2"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"abstract":"<jats:p>Real-world time series data is inherently complex, noisy, and exhibits abrupt changes, posing various challenges in data modeling. Given the ubiquity and importance of time-series data, accurately forecasting change points, instead of the overall predictive performance, has become increasingly attractive as it assists in risk mitigation and loss prevention. In this task, we argue that the past and future interactions involving the target points determine the comprehensive structure contributing to abrupt changes. However, traditional left-to-right auto-regressive approaches only consider the historical sequence, resulting in a flawed learning process and limited performance.<\/jats:p>\n          <jats:p>\n            In this paper, we extend the teacher-student learning and propose a novel\n            <jats:bold>S<\/jats:bold>\n            elf-optimizing\n            <jats:bold>T<\/jats:bold>\n            eacher and\n            <jats:bold>A<\/jats:bold>\n            uto-matching\n            <jats:bold>S<\/jats:bold>\n            tudent framework (named ST-AS) to predict change points in time series data. Our framework models change point representations specific to the target points by integrating future knowledge while avoiding data leakage. Specifically, we design a Gumbel-enhanced filter for our self-optimizing teacher, which constructs selected and filtered sub-groups to derive discriminative representations using a positive-unlabeled learning strategy. Given this well-trained teacher, we propose an adaptive pattern matcher for our auto-matching student model, which learns missing information by automatically aligning relevant features. After that, a novel two-stage dual-guided learning process is then designed to mimic teacher\u2019s decision-making behavior and enhance student\u2019s excavate capability. Finally, we conduct extensive experiments on four real-world datasets to demonstrate that our proposed ST-AS exhibits significantly better prediction performance compared to existing state-of-the-art alternatives.\n          <\/jats:p>","DOI":"10.1145\/3718091","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:50:56Z","timestamp":1745329856000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Self-optimizing Teacher and Auto-matching Student Framework for Change-point Representation Learning in Time Series Forecasting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0119-1916","authenticated-orcid":false,"given":"Jinxiao","family":"Fan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8658-7102","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5040-2468","authenticated-orcid":false,"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Bayesian online changepoint detection. arXiv preprint arXiv:0710.3742","author":"Adams Ryan Prescott","year":"2007","unstructured":"Ryan Prescott Adams and David JC MacKay. 2007. Bayesian online changepoint detection. arXiv preprint arXiv:0710.3742 (2007)."},{"key":"e_1_2_1_2_1","volume-title":"A survey of methods for time series change point detection. Knowledge and information systems 51, 2","author":"Aminikhanghahi Samaneh","year":"2017","unstructured":"Samaneh Aminikhanghahi and Diane J Cook. 2017. A survey of methods for time series change point detection. Knowledge and information systems 51, 2 (2017), 339\u2013367."},{"key":"e_1_2_1_3_1","volume-title":"Caldarelli","author":"Edoardo","year":"2022","unstructured":"Edoardo et al. Caldarelli. 2022. Adaptive Gaussian Process Change Point Detection. In ICML. PMLR, 2542\u20132571."},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1142\/S0218001410007865","article-title":"Change point detection in time series data using support vectors","volume":"24","author":"Camci Fatih","year":"2010","unstructured":"Fatih Camci. 2010. Change point detection in time series data using support vectors. International Journal of Pattern Recognition and Artificial Intelligence 24, 01 (2010), 73\u201395.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"e_1_2_1_5_1","volume-title":"Kernel change-point detection with auxiliary deep generative models. arXiv","author":"Chang Wei-Cheng","year":"2019","unstructured":"Wei-Cheng Chang, Chun-Liang Li, Yiming Yang, and Barnab\u00e1s P\u00f3czos. 2019. Kernel change-point detection with auxiliary deep generative models. arXiv (2019)."},{"key":"e_1_2_1_6_1","doi-asserted-by":"crossref","first-page":"431047","DOI":"10.1155\/2015\/431047","article-title":"Data mining for the internet of things: literature review and challenges","volume":"11","author":"Chen Feng","year":"2015","unstructured":"Feng et al. Chen. 2015. Data mining for the internet of things: literature review and challenges. International Journal of Distributed Sensor Networks 11, 8 (2015), 431047.","journal-title":"International Journal of Distributed Sensor Networks"},{"key":"e_1_2_1_7_1","volume-title":"A teacher-student framework for zero-resource neural machine translation. arXiv preprint arXiv:1705.00753","author":"Chen Yun","year":"2017","unstructured":"Yun Chen, Yang Liu, Yong Cheng, and Victor OK Li. 2017. A teacher-student framework for zero-resource neural machine translation. arXiv preprint arXiv:1705.00753 (2017)."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3087031"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411832"},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Shohreh Deldari Daniel V Smith Hao Xue and Flora D Salim. 2021. Time series change point detection with self-supervised contrastive predictive coding. In WWW. 3124\u20133135.","DOI":"10.1145\/3442381.3449903"},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","first-page":"8331","DOI":"10.1016\/j.atmosenv.2008.07.020","article-title":"A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile","volume":"42","year":"2008","unstructured":"et al. D\u00edaz-Robles. 2008. A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile. Atmospheric Environment 42, 35 (2008), 8331\u20138340.","journal-title":"Atmospheric Environment"},{"key":"e_1_2_1_12_1","volume-title":"LLMAir: Adaptive Reprogramming Large Language Model for Air Quality Prediction. In 2024 IEEE 30th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, 423\u2013430","author":"Fan Jinxiao","year":"2024","unstructured":"Jinxiao Fan, Haolin Chu, Liang Liu, and Huadong Ma. 2024. LLMAir: Adaptive Reprogramming Large Language Model for Air Quality Prediction. In 2024 IEEE 30th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, 423\u2013430."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3702243"},{"key":"e_1_2_1_14_1","volume-title":"Num2Vec: Pre-training Numeric Representations for Time Series Forecasting in Sensing System. ACM Transactions on Sensor Networks","author":"Fan Jinxiao","year":"2023","unstructured":"Jinxiao Fan, Pengfei Wang, Yu Fan, Liang Liu, and Huadong Ma. 2023. Num2Vec: Pre-training Numeric Representations for Time Series Forecasting in Sensing System. ACM Transactions on Sensor Networks (2023)."},{"key":"e_1_2_1_15_1","volume-title":"Predicting Turning Points in Air Quality: A Dual-Guided Denoising Teacher-Student Learning Approach. In China Conference on Wireless Sensor Networks. Springer, 286\u2013300","author":"Fan Jinxiao","year":"2023","unstructured":"Jinxiao Fan, Pengfei Wang, Liang Liu, and Huadong Ma. 2023. Predicting Turning Points in Air Quality: A Dual-Guided Denoising Teacher-Student Learning Approach. In China Conference on Wireless Sensor Networks. Springer, 286\u2013300."},{"key":"e_1_2_1_16_1","volume-title":"Unsupervised scalable representation learning for multivariate time series. Advances in neural information processing systems 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. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/s120912588"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2923982"},{"key":"e_1_2_1_19_1","unstructured":"Geoffrey Hinton Oriol Vinyals Jeff Dean et al. 2015. Distilling the knowledge in a neural network. arXiv 2 7 (2015)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","first-page":"106139","DOI":"10.1016\/j.knosys.2020.106139","article-title":"A deep learning model to effectively capture mutation information in multivariate time series prediction","volume":"203","author":"Hu Jun","year":"2020","unstructured":"Jun Hu and Wendong Zheng. 2020. A deep learning model to effectively capture mutation information in multivariate time series prediction. Knowledge-Based Systems 203 (2020), 106139.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_2_1_21_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv","author":"Jang Eric","year":"2016","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv (2016)."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.030"},{"key":"e_1_2_1_23_1","volume-title":"Change detection in streaming multivariate data using likelihood detectors","author":"Kuncheva Ludmila I","year":"2011","unstructured":"Ludmila I Kuncheva. 2011. Change detection in streaming multivariate data using likelihood detectors. IEEE transactions on knowledge and data engineering 25, 5 (2011), 1175\u20131180."},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Guokun Lai Wei-Cheng Chang Yiming Yang and Hanxiao Liu. 2018. Modeling long-and short-term temporal patterns with deep neural networks. In SIGIR. 95\u2013104.","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_2_1_25_1","volume-title":"Li","author":"Chun-Liang","year":"2017","unstructured":"Chun-Liang et al. Li. 2017. Mmd gan: Towards deeper understanding of moment matching network. NIPS 30 (2017)."},{"key":"e_1_2_1_26_1","volume-title":"MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks","author":"Li Dan","unstructured":"Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, and See-Kiong Ng. 2019. MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks. In ICANN. Springer, 703\u2013716."},{"key":"e_1_2_1_27_1","article-title":"Time-series forecasting with deep learning: a survey","volume":"379","author":"Lim Bryan","year":"2021","unstructured":"Bryan Lim and Stefan Zohren. 2021. Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A 379, 2194 (2021), 20200209.","journal-title":"Philosophical Transactions of the Royal Society A"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2013.01.012"},{"key":"e_1_2_1_29_1","volume-title":"International conference on learning representations.","author":"Liu Shizhan","year":"2021","unstructured":"Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X Liu, and Schahram Dustdar. 2021. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International conference on learning representations."},{"key":"e_1_2_1_30_1","first-page":"18137","article-title":"Learning curves of generic features maps for realistic datasets with a teacher-student model","volume":"34","author":"Loureiro Bruno","year":"2021","unstructured":"Bruno et al. Loureiro. 2021. Learning curves of generic features maps for realistic datasets with a teacher-student model. NIPS 34 (2021), 18137\u201318151.","journal-title":"NIPS"},{"key":"e_1_2_1_31_1","doi-asserted-by":"crossref","unstructured":"George D Montanez Saeed Amizadeh and Nikolay Laptev. 2015. Inertial hidden markov models: Modeling change in multivariate time series. In AAAI.","DOI":"10.1609\/aaai.v29i1.9457"},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-90-481-9482-7","volume-title":"Climate time series analysis. Atmospheric and 397","author":"Mudelsee Manfred","year":"2010","unstructured":"Manfred Mudelsee. 2010. Climate time series analysis. Atmospheric and 397 (2010)."},{"key":"e_1_2_1_33_1","volume-title":"Trend analysis of climate time series: A review of methods. Earth-science reviews 190","author":"Mudelsee Manfred","year":"2019","unstructured":"Manfred Mudelsee. 2019. Trend analysis of climate time series: A review of methods. Earth-science reviews 190 (2019), 310\u2013322."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-015-1955-3"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the 30th ACM international conference on information & knowledge management. 1578\u20131587","author":"Sch\u00e4fer Patrick","year":"2021","unstructured":"Patrick Sch\u00e4fer, Arik Ermshaus, and Ulf Leser. 2021. Clasp-time series segmentation. In Proceedings of the 30th ACM international conference on information & knowledge management. 1578\u20131587."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 4548\u20134557","author":"Serra Joan","year":"2018","unstructured":"Joan Serra, Didac Suris, Marius Miron, and Alexandros Karatzoglou. 2018. Overcoming catastrophic forgetting with hard attention to the task. In International conference on machine learning. PMLR, 4548\u20134557."},{"key":"e_1_2_1_38_1","volume-title":"Self-attention with relative position representations. arXiv preprint arXiv:1803.02155","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05815-0"},{"key":"e_1_2_1_40_1","volume-title":"Unsupervised representation learning for time series with temporal neighborhood coding. arXiv preprint arXiv:2106.00750","author":"Tonekaboni Sana","year":"2021","unstructured":"Sana Tonekaboni, Danny Eytan, and Anna Goldenberg. 2021. Unsupervised representation learning for time series with temporal neighborhood coding. arXiv preprint arXiv:2106.00750 (2021)."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0159"},{"key":"e_1_2_1_42_1","volume-title":"Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks","author":"Wang Lin","year":"2021","unstructured":"Lin Wang and Kuk-Jin Yoon. 2021. Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_2_1_43_1","unstructured":"Zhiyuan Wang Xovee Xu Weifeng Zhang Goce Trajcevski Ting Zhong and Fan Zhou. 2022. Learning Latent Seasonal-Trend Representations for Time Series Forecasting. In Advances in Neural Information Processing Systems."},{"key":"e_1_2_1_44_1","volume-title":"Time series prediction: forecasting the future and understanding the past","author":"Weigend Andreas S","unstructured":"Andreas S Weigend. 2018. Time series prediction: forecasting the future and understanding the past. Routledge."},{"key":"e_1_2_1_45_1","first-page":"4","article-title":"Big data driven marine environment information forecasting: a time series prediction network","volume":"29","author":"Wen Jiabao","year":"2020","unstructured":"Jiabao Wen, Jiachen Yang, Bin Jiang, Houbing Song, and Huihui Wang. 2020. Big data driven marine environment information forecasting: a time series prediction network. IEEE Transactions on Fuzzy Systems 29, 1 (2020), 4\u201318.","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"e_1_2_1_46_1","volume-title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. arXiv preprint arXiv:2210.02186","author":"Wu Haixu","year":"2022","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2022. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. arXiv preprint arXiv:2210.02186 (2022)."},{"key":"e_1_2_1_47_1","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu Haixu","year":"2021","unstructured":"Haixu et al. Wu. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NIPs 34 (2021), 22419\u201322430.","journal-title":"NIPs"},{"key":"e_1_2_1_48_1","volume-title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy. arXiv","author":"Xu Jiehui","year":"2021","unstructured":"Jiehui Xu, Haixu Wu, Jianmin Wang, and Mingsheng Long. 2021. Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy. arXiv (2021)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/2540128.2540390"},{"key":"e_1_2_1_50_1","volume-title":"Regularized graph structure learning with semantic knowledge for multi-variates time-series forecasting. arXiv","year":"2022","unstructured":"et al. Yu, Hongyuan. 2022. Regularized graph structure learning with semantic knowledge for multi-variates time-series forecasting. arXiv (2022)."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"e_1_2_1_52_1","volume-title":"Zheng","author":"Yu","year":"2015","unstructured":"Yu et al. Zheng. 2015. Forecasting fine-grained air quality based on big data. In KDD. 2267\u20132276."},{"key":"e_1_2_1_53_1","volume-title":"Zhou","author":"Haoyi","year":"2021","unstructured":"Haoyi et al. Zhou. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI."},{"key":"e_1_2_1_54_1","volume-title":"International conference on machine learning. PMLR, 27268\u201327286","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 International conference on machine learning. PMLR, 27268\u201327286."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:51:11Z","timestamp":1745329871000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":54,"alternative-id":["10.1145\/3718091"],"URL":"https:\/\/doi.org\/10.1145\/3718091","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2023-07-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3718091"}}