{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:03:01Z","timestamp":1781283781473,"version":"3.54.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001779","name":"Monash University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001779","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We argue that time series analysis is fundamentally different in nature to either vision or natural language processing with respect to the forms of meaningful self-supervised learning tasks that can be defined. Motivated by this insight, we introduce a novel approach called <jats:italic>Series2Vec<\/jats:italic> for self-supervised representation learning. Unlike the state-of-the-art methods in time series which rely on hand-crafted data augmentation, Series2Vec is trained by predicting the similarity between two series in both temporal and spectral domains through a self-supervised task. By leveraging the similarity prediction task, which has inherent meaning for a wide range of time series analysis tasks, Series2Vec eliminates the need for hand-crafted data augmentation. To further enforce the network to learn similar representations for similar time series, we propose a novel approach that applies order-invariant attention to each representation within the batch during training. Our evaluation of Series2Vec on nine large real-world datasets, along with the UCR\/UEA archive, shows enhanced performance compared to current state-of-the-art self-supervised techniques for time series. Additionally, our extensive experiments show that Series2Vec performs comparably with fully supervised training and offers high efficiency in datasets with limited-labeled data. Finally, we show that the fusion of Series2Vec with other representation learning models leads to enhanced performance for time series classification. Code and models are open-source at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Navidfoumani\/Series2Vec\">https:\/\/github.com\/Navidfoumani\/Series2Vec<\/jats:ext-link><\/jats:p>","DOI":"10.1007\/s10618-024-01043-w","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T07:02:07Z","timestamp":1718866927000},"page":"2520-2544","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Series2vec: similarity-based self-supervised representation learning for time series classification"],"prefix":"10.1007","volume":"38","author":[{"given":"Navid Mohammadi","family":"Foumani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang Wei","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey I.","family":"Webb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahsa","family":"Salehi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"issue":"6","key":"1043_CR1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.061907","volume":"64","author":"RG Andrzejak","year":"2001","unstructured":"Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE (2001) Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E 64(6):061907","journal-title":"Phys Rev E"},{"key":"1043_CR2","first-page":"3","volume":"3","author":"D Anguita","year":"2013","unstructured":"Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL et al (2013) A public domain dataset for human activity recognition using smartphones. Esann 3:3","journal-title":"Esann"},{"key":"1043_CR3","unstructured":"Bagnall A, Dau HA, Lines J, Flynn M, Large J, Bostrom A, Southam P, Keogh E (2018) The UEA multivariate time series classification archive. Preprint arXiv:1811.00075"},{"issue":"15","key":"1043_CR4","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1016\/j.patrec.2012.12.014","volume":"34","author":"R Chavarriaga","year":"2013","unstructured":"Chavarriaga R, Sagha H, Calatroni A, Digumarti ST, Tr\u00f6ster G, Mill\u00e1n JDR, Roggen D (2013) The opportunity challenge: a benchmark database for on-body sensor-based activity recognition. Pattern Recognit Lett 34(15):2033\u20132042","journal-title":"Pattern Recognit Lett"},{"key":"1043_CR5","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp 1597\u20131607"},{"issue":"1","key":"1043_CR6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/TE.1969.4320436","volume":"12","author":"JW Cooley","year":"1969","unstructured":"Cooley JW, Lewis PA, Welch PD (1969) The fast Fourier transform and its applications. IEEE Trans Educ 12(1):27\u201334","journal-title":"IEEE Trans Educ"},{"key":"1043_CR7","unstructured":"Cuturi M, Blondel M (2017) Soft-DTW: a differentiable loss function for time-series. In: International conference on machine learning. PMLR, pp 894\u2013903"},{"issue":"6","key":"1043_CR8","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1109\/JAS.2019.1911747","volume":"6","author":"HA Dau","year":"2019","unstructured":"Dau HA, Bagnall A, Kamgar K, Yeh C-CM, Zhu Y, Gharghabi S, Ratanamahatana CA, Keogh E (2019) The UCR time series archive. IEEE\/CAA J Autom Sin 6(6):1293\u20131305","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"1043_CR9","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: ACL, 1, 4171\u20134186"},{"key":"1043_CR10","doi-asserted-by":"crossref","unstructured":"Eldele E, Ragab M, Chen Z, Wu M, Kwoh CK, Li X, Guan C (2021) Time-series representation learning via temporal and contextual contrasting. In: IJCAI-21, pp 2352\u20132359","DOI":"10.24963\/ijcai.2021\/324"},{"issue":"4","key":"1043_CR11","first-page":"917","volume":"33","author":"HI Fawaz","year":"2019","unstructured":"Fawaz HI, Forestier G, Weber J, Idoumghar L, Muller P-A (2019) Deep learning for time series classification: a review. DMKD 33(4):917\u2013963","journal-title":"DMKD"},{"key":"1043_CR12","doi-asserted-by":"crossref","unstructured":"Foumani SNM, Tan CW, Salehi M (2021) Disjoint-CNN for multivariate time series classification. In: 2021 international conference on data mining workshops (ICDMW). IEEE, pp 760\u2013769","DOI":"10.1109\/ICDMW53433.2021.00099"},{"key":"1043_CR13","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s10618-023-00948-2","volume":"38","author":"NM Foumani","year":"2023","unstructured":"Foumani NM, Tan CW, Webb GI, Salehi M (2023) Improving position encoding of transformers for multivariate time series classification. Data Min Knowl Discov 38:22\u201348","journal-title":"Data Min Knowl Discov"},{"key":"1043_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649448","volume":"56","author":"NM Foumani","year":"2024","unstructured":"Foumani NM, Miller L, Tan CW, Webb GI, Forestier G, Salehi M (2024) Deep learning for time series classification and extrinsic regression: a current survey. ACM Comput Surv 56:1\u201345","journal-title":"ACM Comput Surv"},{"key":"1043_CR15","unstructured":"Foumani NM, Mackellar G, Ghane S, Irtza S, Nguyen N, Salehi M (2024) Eeg2rep: enhancing self-supervised EEG representation through informative masked inputs. Preprint arXiv:2402.17772"},{"key":"1043_CR16","unstructured":"Franceschi J-Y, Dieuleveut A, Jaggi M (2019) Unsupervised scalable representation learning for multivariate time series. NeurIPS 32"},{"key":"1043_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-CNN. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"issue":"23","key":"1043_CR18","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE (2000) Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23):215\u2013220","journal-title":"Circulation"},{"key":"1043_CR19","unstructured":"Goyal P, Caron M, Lefaudeux B, Xu M, Wang P, Pai V, Singh M, Liptchinsky V, Misra I, Joulin A et al (2021) Self-supervised pretraining of visual features in the wild. Preprint arXiv:2103.01988"},{"key":"1043_CR20","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill J-B, Strub F, Altch\u00e9 F, Tallec C, Richemond P, Buchatskaya E, Doersch C, Avila Pires B, Guo Z, Gheshlaghi Azar M et al (2020) Bootstrap your own latent-a new approach to self-supervised learning. NeurIPS 33:21271\u201321284","journal-title":"NeurIPS"},{"key":"1043_CR21","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1043_CR22","doi-asserted-by":"crossref","unstructured":"Herrmann M, Webb GI (2023) Amercing: an intuitive and effective constraint for dynamic time warping. Pattern Recognit 109333","DOI":"10.1016\/j.patcog.2023.109333"},{"key":"1043_CR23","unstructured":"Ismail-Fawaz A, Dempster A, Tan CW, Herrmann M, Miller L, Schmidt DF, Berretti S, Weber J, Devanne M, Forestier G et al (2023) An approach to multiple comparison benchmark evaluations that is stable under manipulation of the comparate set. Preprint arXiv:2305.11921"},{"issue":"9","key":"1043_CR24","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1016\/j.patcog.2010.09.022","volume":"44","author":"Y-S Jeong","year":"2011","unstructured":"Jeong Y-S, Jeong MK, Omitaomu OA (2011) Weighted dynamic time warping for time series classification. Pattern Recognit 44(9):2231\u20132240","journal-title":"Pattern Recognit"},{"key":"1043_CR25","first-page":"283","volume":"30","author":"RJ Kate","year":"2016","unstructured":"Kate RJ (2016) Using dynamic time warping distances as features for improved time series classification. DMKD 30:283\u2013312","journal-title":"DMKD"},{"key":"1043_CR26","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Preprint arXiv:1412.6980"},{"key":"1043_CR27","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.653659","volume":"15","author":"D Kostas","year":"2021","unstructured":"Kostas D, Aroca-Ouellette S, Rudzicz F (2021) Bendr: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data. Front Hum Neurosci 15:653659","journal-title":"Front Hum Neurosci"},{"key":"1043_CR28","doi-asserted-by":"crossref","unstructured":"Lei Q, Yi J, Vaculin R, Wu L, Dhillon IS (2019) Similarity preserving representation learning for time series clustering. In: 28th international joint conference on artificial intelligence, pp 2845\u20132851","DOI":"10.24963\/ijcai.2019\/394"},{"key":"1043_CR29","doi-asserted-by":"crossref","unstructured":"Lockhart JW, Pulickal T, Weiss GM (2012) Applications of mobile activity recognition. In: Conference on ubiquitous computing, pp 1054\u20131058","DOI":"10.1145\/2370216.2370441"},{"issue":"3","key":"1043_CR30","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1016\/j.patcog.2010.09.013","volume":"44","author":"F Petitjean","year":"2011","unstructured":"Petitjean F, Ketterlin A, Gan\u00e7arski P (2011) A global averaging method for dynamic time warping, with applications to clustering. Pattern Recognit 44(3):678\u2013693","journal-title":"Pattern Recognit"},{"issue":"1","key":"1043_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, Liu PJ, Liu X, Marcus J, Sun M et al (2018) Scalable and accurate deep learning with electronic health records. NPJ Digit Med 1(1):1\u201310","journal-title":"NPJ Digit Med"},{"key":"1043_CR32","doi-asserted-by":"crossref","unstructured":"Reiss A, Stricker D (2012) Introducing a new benchmarked dataset for activity monitoring. In: International symposium on wearable computers, pp 108\u2013109","DOI":"10.1109\/ISWC.2012.13"},{"key":"1043_CR33","first-page":"65","volume":"3","author":"H Sakoe","year":"1971","unstructured":"Sakoe H, Chiba S (1971) A dynamic programming approach to continuous speech recognition. Int Congr Acoust 3:65\u201369","journal-title":"Int Congr Acoust"},{"key":"1043_CR34","first-page":"1032","volume":"35","author":"CW Tan","year":"2021","unstructured":"Tan CW, Bergmeir C, Petitjean F, Webb GI (2021) Time series extrinsic regression: predicting numeric values from time series data. DMKD 35:1032\u20131060","journal-title":"DMKD"},{"key":"1043_CR35","unstructured":"Tonekaboni S, Eytan D, Goldenberg A (2021) Unsupervised representation learning for time series with temporal neighborhood coding. Preprint arXiv:2106.00750"},{"key":"1043_CR36","unstructured":"van\u00a0den Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. Preprint arXiv:1807.03748"},{"key":"1043_CR37","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"1043_CR38","unstructured":"Weiss GM, Lockhart J (2012) The impact of personalization on smartphone-based activity recognition. In: Workshops at AAAI"},{"key":"1043_CR39","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.patrec.2022.02.007","volume":"155","author":"K Wickstr\u00f8m","year":"2022","unstructured":"Wickstr\u00f8m K, Kampffmeyer M, Mikalsen K\u00d8, Jenssen R (2022) Mixing up contrastive learning: self-supervised representation learning for time series. Pattern Recognit Lett. 155:54\u201361","journal-title":"Pattern Recognit Lett."},{"key":"1043_CR40","unstructured":"Yang L, Hong S (2022) Unsupervised time-series representation learning with iterative bilinear temporal-spectral fusion. In: International conference on machine learning, pp 25038\u201325054"},{"key":"1043_CR41","doi-asserted-by":"publisher","first-page":"8980","DOI":"10.1609\/aaai.v36i8.20881","volume":"36","author":"Z Yue","year":"2022","unstructured":"Yue Z, Wang Y, Duan J, Yang T, Huang C, Tong Y, Xu B (2022) Ts2vec: towards universal representation of time series. AAAI 36:8980\u20138987","journal-title":"AAAI"},{"issue":"3","key":"1043_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2345770.2345781","volume":"11","author":"P Zappi","year":"2012","unstructured":"Zappi P, Roggen D, Farella E, Tr\u00f6ster G, Benini L (2012) Network-level power-performance trade-off in wearable activity recognition: a dynamic sensor selection approach. Trans Embed Comput Syst 11(3):1\u201330","journal-title":"Trans Embed Comput Syst"},{"key":"1043_CR43","doi-asserted-by":"crossref","unstructured":"Zerveas G, Jayaraman S, Patel D, Bhamidipaty A, Eickhoff C (2021) A transformer-based framework for multivariate time series representation learning. In: SIGKDD, pp 2114\u20132124","DOI":"10.1145\/3447548.3467401"},{"key":"1043_CR44","doi-asserted-by":"crossref","unstructured":"Zhang M, Sawchuk AA (2012) USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors. In: Conference on ubiquitous computing, pp 1036\u20131043","DOI":"10.1145\/2370216.2370438"},{"key":"1043_CR45","unstructured":"Zhang X, Zhao Z, Tsiligkaridis T, Zitnik M (2022) Self-supervised contrastive pre-training for time series via time-frequency consistency. In: Proceedings of neural information processing systems. NeurIPS"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-024-01043-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-024-01043-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-024-01043-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T10:05:50Z","timestamp":1722333950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-024-01043-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1043"],"URL":"https:\/\/doi.org\/10.1007\/s10618-024-01043-w","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"4 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}