{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:29:11Z","timestamp":1780054151782,"version":"3.54.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Fudan Institute on Networking System of AI"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Semi-supervised learning (SSL) can utilize a large amount of unlabeled data for self-training and continuous evolution with only a few annotations. This feature makes SSL a potential candidate for dealing with data from changing and real-time environments, where deep-learning models need to be adapting to evolving and nonstable (non-i.i.d.) data streams from the real world, i.e., online evolutive scenarios. However, state-of-the-art SSL methods often have complex model design mechanisms and may cause performance degradation in a generalized and open environment. In an edge computing setup, e.g., typical in modern Internet of Things (IoT) applications, a multi-agent SSL architecture can help resolve generalization problems by sharing knowledge between models. In this paper, we introduce Mutual Match (MM), an online-evolutive SSL algorithm that integrates mutual interactive learning and soft-supervision consistency regularization, as well as unsupervised sample mining. By leveraging extra knowledge in the training process and the interactive collaboration between models, MM surpasses multiple top SSL algorithms in accuracy and convergence efficiency under the same online-evolutive experiment setup. MM simplifies the complexity of model design and follows a unified and easy-to-expandable pipeline, which can be beneficial to tasks with insufficient labeled data and frequently changing data distribution.<\/jats:p>","DOI":"10.1007\/s10489-022-03564-7","type":"journal-article","created":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T08:33:09Z","timestamp":1653726789000},"page":"3336-3350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Mutual match for semi-supervised online evolutive learning"],"prefix":"10.1007","volume":"53","author":[{"given":"Di","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoguang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,28]]},"reference":[{"issue":"2","key":"3564_CR1","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","volume":"109","author":"JE Van Engelen","year":"2020","unstructured":"Van Engelen JE, Hoos HH (2020) A survey on semi-supervised learning. Mach Learn 109 (2):373\u2013440","journal-title":"Mach Learn"},{"key":"3564_CR2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.patcog.2016.11.003","volume":"64","author":"R Sheikhpour","year":"2017","unstructured":"Sheikhpour R, Sarram MA, Gharaghani S, Chahooki MAZ (2017) A survey on semi-supervised feature selection methods. Pattern Recogn 64:141\u2013158","journal-title":"Pattern Recogn"},{"key":"3564_CR3","doi-asserted-by":"crossref","unstructured":"Zhai X, Kolesnikov A, Houlsby N, Beyer L (2021) Scaling vision transformers. arXiv:2106.04560","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"3564_CR4","unstructured":"Riquelme C, Puigcerver J, Mustafa B, Neumann M, Jenatton R, Pinto AS, Keysers D, Houlsby N (2021) Scaling vision with sparse mixture of experts. arXiv:2106.05974"},{"issue":"8","key":"3564_CR5","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","volume":"107","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proc IEEE 107(8):1738\u20131762","journal-title":"Proc IEEE"},{"key":"3564_CR6","unstructured":"Zeng X, Pang C, Jiang L, Song L, Yang K, et al. (2020) White paper on networking systems of AI. https:\/\/ainsai.org\/RESOURCES\/White%20Paper\/whitepaper.pdf"},{"key":"3564_CR7","unstructured":"Berthelot D, Carlini N, Goodfellow IJ, Papernot N, Oliver A, Raffel C (2019) Mixmatch: A holistic approach to semi-supervised learning. In: NeurIPS, pp 5050\u20135060"},{"key":"3564_CR8","unstructured":"Sohn K, Berthelot D, Carlini N, Zhang Z, Zhang H, Raffel C, Cubuk ED, Kurakin A, Li CL (2020) Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In: NeurIPS"},{"key":"3564_CR9","doi-asserted-by":"crossref","unstructured":"Arazo E, Ortego D, Albert P, O\u2019Connor N E, McGuinness K (2020) Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: IJCNN. IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"3564_CR10","unstructured":"Bachman P, Alsharif O, Precup D (2014) Learning with pseudo-ensembles. In: NIPS, pp 3365\u20133373"},{"issue":"1","key":"3564_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TBDATA.2018.2850013","volume":"6","author":"D Zhang","year":"2018","unstructured":"Zhang D, Yin J, Zhu X, Zhang C (2018) Network representation learning: A survey. IEEE transactions on Big Data 6(1):3\u201328","journal-title":"IEEE transactions on Big Data"},{"key":"3564_CR12","unstructured":"Lee D-H (2013) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML, vol 3, p 896"},{"key":"3564_CR13","unstructured":"Sajjadi M, Javanmardi M, Tasdizen T (2016) Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In: NIPS, pp 1163\u20131171"},{"key":"3564_CR14","unstructured":"Tarvainen A, Valpola H (2017) Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS, pp 1195\u20131204"},{"key":"3564_CR15","unstructured":"Laine S, Aila T (2017) Temporal ensembling for semi-supervised learning. In: ICLR (poster). OpenReview.net"},{"key":"3564_CR16","unstructured":"Liu L, Li Y, Tan RT (2019) Decoupled certainty-driven consistency loss for semi-supervised learning. arXiv:1901.05657"},{"key":"3564_CR17","unstructured":"Xie Q, Dai Z, Hovy EH, Luong T, Le Q (2020) Unsupervised data augmentation for consistency training. In: NeurIPS"},{"key":"3564_CR18","unstructured":"Berthelot D, Carlini N, Cubuk ED, Kurakin A, Sohn K, Zhang H, Raffel C (2020) Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring. In: ICLR. OpenReview.net"},{"key":"3564_CR19","doi-asserted-by":"crossref","unstructured":"Sajjadi M, Javanmardi M, Tasdizen T (2016) Mutual exclusivity loss for semi-supervised deep learning. In: 2016 IEEE International Conference on Image Processing (ICIP). IEEE, pp 1908\u20131912","DOI":"10.1109\/ICIP.2016.7532690"},{"key":"3564_CR20","unstructured":"Grandvalet Y, Bengio Y (2004) Semi-supervised learning by entropy minimization. In: NIPS, pp 529\u2013536"},{"key":"3564_CR21","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le QV (2020) Randaugment: Practical automated data augmentation with a reduced search space. In: CVPR workshops. Computer Vision Foundation \/ IEEE, pp 3008\u20133017","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"3564_CR22","doi-asserted-by":"crossref","unstructured":"Nassar I, Herath S, Abbasnejad E, Buntine WL, Haffari G (2021) All labels are not created equal: Enhancing semi-supervision via label grouping and co-training. In: CVPR. Computer Vision Foundation \/ IEEE, pp 7241\u20137250","DOI":"10.1109\/CVPR46437.2021.00716"},{"key":"3564_CR23","unstructured":"Springenberg JT (2016) Unsupervised and semi-supervised learning with categorical generative adversarial networks. In: ICLR (poster)"},{"key":"3564_CR24","unstructured":"Odena A (2016) Semi-supervised learning with generative adversarial networks. arXiv:1606.01583"},{"key":"3564_CR25","unstructured":"Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: ICLR"},{"key":"3564_CR26","unstructured":"Hjelm RD, Fedorov A, Lavoie-Marchildon S, Grewal K, Bachman P, Trischler A, Bengio Y (2019) Learning deep representations by mutual information estimation and maximization. In: ICLR. OpenReview.net"},{"key":"3564_CR27","doi-asserted-by":"crossref","unstructured":"Jing L, Tian Y (2020) Self-supervised visual feature learning with deep neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"3564_CR28","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G E (2020) A simple framework for contrastive learning of visual representations. In: ICML. Proceedings of Machine Learning Research, vol 119. PMLR, pp 1597\u20131607"},{"key":"3564_CR29","unstructured":"Chen T, Kornblith S, Swersky K, Norouzi M, Hinton GE (2020) Big self-supervised models are strong semi-supervised learners. In: NeurIPS"},{"key":"3564_CR30","unstructured":"Kim B, Choo J, Kwon Y-D, Joe S, Min S, Gwon Y (2021) Selfmatch: Combining contrastive self-supervision and consistency for semi-supervised learning. arXiv:2101.06480"},{"key":"3564_CR31","doi-asserted-by":"crossref","unstructured":"Blum A, Mitchell TM (1998) Combining labeled and unlabeled data with co-training. In: COLT. ACM, pp 92\u2013100","DOI":"10.1145\/279943.279962"},{"key":"3564_CR32","doi-asserted-by":"crossref","unstructured":"Nigam K, Ghani R (2000) Analyzing the effectiveness and applicability of co-training. In: CIKM. ACM, pp 86\u201393","DOI":"10.1145\/354756.354805"},{"issue":"11","key":"3564_CR33","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","volume":"17","author":"Z-H Zhou","year":"2005","unstructured":"Zhou Z-H, Li M (2005) Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on knowledge and Data Engineering 17(11):1529\u20131541","journal-title":"IEEE Transactions on knowledge and Data Engineering"},{"key":"3564_CR34","doi-asserted-by":"crossref","unstructured":"Davison AC, Hinkley DV (1997) Bootstrap methods and their application, Cambridge University Press","DOI":"10.1017\/CBO9780511802843"},{"key":"3564_CR35","doi-asserted-by":"crossref","unstructured":"Chen D, Wang W, Gao W, Zhou Z-H (2018) Tri-net for semi-supervised deep learning. In: IJCAI. ijcai.org, pp 2014\u20132020","DOI":"10.24963\/ijcai.2018\/278"},{"issue":"3","key":"3564_CR36","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1007682208299","volume":"40","author":"L Breiman","year":"2000","unstructured":"Breiman L (2000) Randomizing outputs to increase prediction accuracy. Mach Learn 40(3):229\u2013242","journal-title":"Mach Learn"},{"key":"3564_CR37","unstructured":"Hinton GE, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"3564_CR38","doi-asserted-by":"crossref","unstructured":"Zhang Y, Xiang T, Hospedales TM, Lu H (2018) Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4320\u20134328","DOI":"10.1109\/CVPR.2018.00454"},{"key":"3564_CR39","unstructured":"Pereyra G, Tucker G, Chorowski J, Kaiser L, Hinton G E (2017) Regularizing neural networks by penalizing confident output distributions. In: ICLR (workshop). OpenReview.net"},{"key":"3564_CR40","doi-asserted-by":"crossref","unstructured":"Pham H, Dai Z, Xie Q, Le QV (2021) Meta pseudo labels. In: CVPR. Computer Vision Foundation \/ IEEE, pp 11557\u201311568","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"3564_CR41","doi-asserted-by":"crossref","unstructured":"Sellars P, Avil\u00e9s-Rivero AI, Sch\u00f6nlieb C-B (2021) Laplacenet: A hybrid energy-neural model for deep semi-supervised classification. arXiv:2106.04527","DOI":"10.1109\/TNNLS.2022.3203315"},{"key":"3564_CR42","doi-asserted-by":"crossref","unstructured":"Li E, Zhou Z, Chen X (2018) Edge intelligence: On-demand deep learning model co-inference with device-edge synergy. In: MECOMM@SIGCOMM. ACM, pp 31\u201336","DOI":"10.1145\/3229556.3229562"},{"key":"3564_CR43","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning, MIT press"},{"key":"3564_CR44","unstructured":"Xie Q, Dai Z, Hovy EH, Luong T, Le Q (2020) Unsupervised data augmentation for consistency training. In: NeurIPS"},{"key":"3564_CR45","first-page":"2","volume":"2","author":"G Hinton","year":"2014","unstructured":"Hinton G, Vinyals O, Dean J (2014) Dark knowledge. Presented as the keynote in BayLearn 2:2","journal-title":"Presented as the keynote in BayLearn"},{"key":"3564_CR46","unstructured":"G\u00e9ron A (2019) Hands-on machine learning with scikit-learn, keras, and tensorflow: Concepts, tools, and techniques to build intelligent systems, O\u2019Reilly Media"},{"key":"3564_CR47","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M (2016) Tensorflow: A system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265\u2013283"},{"key":"3564_CR48","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. In: BMVC. BMVA Press","DOI":"10.5244\/C.30.87"},{"key":"3564_CR49","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV. IEEE Computer Society, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"3564_CR50","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bottou L, Orr GB, M\u00fcller K-R (2012) Efficient backprop, Lecture Notes in Computer Science, vol 7700. Springer","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"3564_CR51","unstructured":"Loshchilov I, Hutter F (2017) SGDR: stochastic gradient descent with warm restarts. In: ICLR (poster). OpenReview.net"},{"key":"3564_CR52","unstructured":"Jung A B, Wada K, Crall J, Tanaka S, Graving J, Reinders C, Yadav S, Banerjee J, Vecsei G, Kraft A, Rui Z, Borovec J, Vallentin C, Zhydenko S, Pfeiffer K, Cook B, Fern\u00e1ndez I, De Rainville F -M, Weng C-H, Ayala-Acevedo A, Meudec R, Laporte M et al (2020) imgaug. Online; accessed 01-Feb-2020"},{"key":"3564_CR53","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images"},{"key":"3564_CR54","unstructured":"Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng A Y (2011) Reading digits in natural images with unsupervised feature learning"},{"key":"3564_CR55","unstructured":"Le Y, Yang X (2015) Tiny imagenet visual recognition challenge. CS 231N 7(7):3"},{"key":"3564_CR56","unstructured":"Zhang H, Ciss\u00e9 M, Dauphin Y N, Lopez-Paz D (2018) mixup: Beyond empirical risk minimization. In: ICLR (poster). OpenReview.net"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03564-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03564-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03564-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T11:08:39Z","timestamp":1673435319000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03564-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,28]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["3564"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03564-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,28]]},"assertion":[{"value":"29 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}