{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:47:12Z","timestamp":1772776032046,"version":"3.50.1"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. Army Research Office Award","award":["W911NF-17-1-0367"],"award-info":[{"award-number":["W911NF-17-1-0367"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,2,28]]},"abstract":"<jats:p>Multi-label learning recovers multiple labels from a single instance. It is a more challenging task compared with single-label manner. Most multi-label learning approaches need large-scale well-labeled samples to achieve high accurate performance. However, it is expensive to build such a dataset. In this work, we propose a generic multi-label learning framework based on Adaptive Graph and Marginalized Augmentation (AGMA) in a semi-supervised scenario. Generally speaking, AGMA makes use of a small amount of labeled data associated with a lot of unlabeled data to boost the learning performance. First, an adaptive similarity graph is learned to effectively capture the intrinsic structure within the data. Second, marginalized augmentation strategy is explored to enhance the model generalization and robustness. Third, a feature-label autoencoder is further deployed to improve inferring efficiency. All the modules are jointly trained to benefit each other. State-of-the-art benchmarks in both traditional and zero-shot multi-label learning scenarios are evaluated. Experiments and ablation studies illustrate the accuracy and efficiency of our AGMA method.<\/jats:p>","DOI":"10.1145\/3451884","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T21:06:18Z","timestamp":1626815178000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Generic Multi-label Annotation via Adaptive Graph and Marginalized Augmentation"],"prefix":"10.1145","volume":"16","author":[{"given":"Lichen","family":"Wang","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengming","family":"Ding","sequence":"additional","affiliation":[{"name":"Tulane University, New Orleans, LA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/361573.361582"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.009"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/993483"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2500491"},{"key":"e_1_2_1_6_1","volume-title":"Proceeding of the IEEE International Workshop on Machine Learning for Signal Processing. 1\u20138.","author":"Briggs F.","unstructured":"F. Briggs , B. Lakshminarayanan , L. Neal , X. Z. Fern , R. Raich , S. J. K. Hadley , A. S. Hadley , and M. G. Betts . 2013. New methods for acoustic classification of multiple simultaneous bird species in a noisy environment . In Proceeding of the IEEE International Workshop on Machine Learning for Signal Processing. 1\u20138. F. Briggs, B. Lakshminarayanan, L. Neal, X. Z. Fern, R. Raich, S. J. K. Hadley, A. S. Hadley, and M. G. Betts. 2013. New methods for acoustic classification of multiple simultaneous bird species in a noisy environment. In Proceeding of the IEEE International Workshop on Machine Learning for Signal Processing. 1\u20138."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1841234"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1931390.1931406"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045057"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3043079"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/28395.28396"},{"key":"e_1_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jia Deng Wei Dong Richard Socher Lijia Li Kai Li and Feifei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 248\u2013255.  Jia Deng Wei Dong Richard Socher Lijia Li Kai Li and Feifei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.29"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Tao Xiang Elyor Kodirov and Shagong Gong. 2017. Semantic autoencoder for zero-shot learning. In Proceeding of the IEEE Computer Vision and Pattern Recognition.  Tao Xiang Elyor Kodirov and Shagong Gong. 2017. Semantic autoencoder for zero-shot learning. In Proceeding of the IEEE Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1099554.1099591"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24775-3_5"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0113"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319911"},{"key":"e_1_2_1_20_1","volume-title":"Jiancheng Lv, and Xi Peng.","author":"Huang Zhenyu","year":"2020","unstructured":"Zhenyu Huang , Peng Hu , Joey Tianyi Zhou , Jiancheng Lv, and Xi Peng. 2020 . Partially view-aligned clustering. Proceeding of the Neural Information Processing Systems . Zhenyu Huang, Peng Hu, Joey Tianyi Zhou, Jiancheng Lv, and Xi Peng. 2020. Partially view-aligned clustering. Proceeding of the Neural Information Processing Systems."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1754428.1754431"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2887094"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICBK.2017.12"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.09.009"},{"key":"e_1_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Christoph H. Lampert Hannes Nickisch and Stefan Harmeling. 2009. Learning to detect unseen object classes by between-class attribute transfer. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 951\u2013958.  Christoph H. Lampert Hannes Nickisch and Stefan Harmeling. 2009. Learning to detect unseen object classes by between-class attribute transfer. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 951\u2013958.","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3015997"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1178677.1178689"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3176838"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2794976"},{"key":"e_1_2_1_31_1","volume-title":"Optimal lockdown for pandemic control. arXiv preprint arXiv:2010.12923","author":"Ma Qianqian","year":"2020","unstructured":"Qianqian Ma , Yang-Yu Liu , and Alex Olshevsky . 2020. Optimal lockdown for pandemic control. arXiv preprint arXiv:2010.12923 ( 2020 ). Qianqian Ma, Yang-Yu Liu, and Alex Olshevsky. 2020. Optimal lockdown for pandemic control. arXiv preprint arXiv:2010.12923 (2020)."},{"key":"e_1_2_1_32_1","volume-title":"Proceeding of the Advances in Neural Information Processing Systems","volume":"33","author":"Ma Qianqian","year":"2020","unstructured":"Qianqian Ma and Alex Olshevsky . 2020 . Adversarial crowdsourcing through robust rank-one matrix completion . In Proceeding of the Advances in Neural Information Processing Systems , Vol. 33 . Curran Associates, Inc., 2 1841\u201321852. Qianqian Ma and Alex Olshevsky. 2020. Adversarial crowdsourcing through robust rank-one matrix completion. In Proceeding of the Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 21841\u201321852."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3042865"},{"key":"e_1_2_1_34_1","volume-title":"Marginalizing corrupted features. arXiv preprint arXiv:1402.7001","author":"Maaten Laurens","year":"2014","unstructured":"Laurens Maaten , Minmin Chen , Stephen Tyree , and Kilian Weinberger . 2014. Marginalizing corrupted features. arXiv preprint arXiv:1402.7001 ( 2014 ). Laurens Maaten, Minmin Chen, Stephen Tyree, and Kilian Weinberger. 2014. Marginalizing corrupted features. arXiv preprint arXiv:1402.7001 (2014)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298586"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2161607"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886761"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3016004"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2984093.2984252"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355028"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2958324"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291245"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3363573"},{"key":"e_1_2_1_44_1","volume-title":"International Conference on Learning Representations.","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014 . Very deep convolutional networks for large-scale image recognition . International Conference on Learning Representations. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations."},{"key":"e_1_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 1\u20139.  Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceeding of the IEEE Computer Vision and Pattern Recognition. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_46_1","volume-title":"Vlahavas","author":"Trohidis Konstantinos","year":"2008","unstructured":"Konstantinos Trohidis , Grigorios Tsoumakas , George Kalliris , and Ioannis P . Vlahavas . 2008 . Multi-label classification of music into emotions. In Proceeding of the ISMIR. 325\u2013330. Konstantinos Trohidis, Grigorios Tsoumakas, George Kalliris, and Ioannis P. Vlahavas. 2008. Multi-label classification of music into emotions. In Proceeding of the ISMIR. 325\u2013330."},{"key":"e_1_2_1_47_1","unstructured":"C. Wah S. Branson P. Welinder P. Perona and S. Belongie. 2011. The Caltech-UCSD Birds-200-2011 Dataset. Technical Report.  C. Wah S. Branson P. Welinder P. Perona and S. Belongie. 2011. The Caltech-UCSD Birds-200-2011 Dataset. Technical Report."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304889.3305049"},{"key":"e_1_2_1_49_1","volume-title":"Proceeding of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Wang Lichen","year":"2018","unstructured":"Lichen Wang , Zhengming Ding , and Yun Fu . 2018 . Learning transferable subspace for human motion segmentation . In Proceeding of the AAAI Conference on Artificial Intelligence , Vol. 32 . Lichen Wang, Zhengming Ding, and Yun Fu. 2018. Learning transferable subspace for human motion segmentation. In Proceeding of the AAAI Conference on Artificial Intelligence, Vol. 32."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2870945"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00631"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2810515"},{"key":"e_1_2_1_53_1","volume-title":"Technical Report","author":"Welinder Peter","year":"2010","unstructured":"Peter Welinder , Steve Branson , Takeshi Mita , Catherine Wah , Florian Schroff , Serge Belongie , and Pietro Perona . 2010. Caltech- UCSD Birds 200. Technical Report . California Institute of Technology . CNS-TR- 2010 -001. 2010. Peter Welinder, Steve Branson, Takeshi Mita, Catherine Wah, Florian Schroff, Serge Belongie, and Pietro Perona. 2010. Caltech-UCSD Birds 200. Technical Report. California Institute of Technology. CNS-TR-2010-001. 2010."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.473"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_50"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2008.11.009"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499907.2499910"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1839490.1839495"},{"key":"e_1_2_1_59_1","first-page":"1","article-title":"Multi-class heterogeneous domain adaptation","volume":"20","author":"Zhou Joey Tianyi","year":"2019","unstructured":"Joey Tianyi Zhou , Ivor W. Tsang , Sinno Jialin Pan , and Mingkui Tan . 2019 . Multi-class heterogeneous domain adaptation . Journal of Machine Learning Research 20 , 57 (2019), 1 \u2013 31 . Joey Tianyi Zhou, Ivor W. Tsang, Sinno Jialin Pan, and Mingkui Tan. 2019. Multi-class heterogeneous domain adaptation. Journal of Machine Learning Research 20, 57 (2019), 1\u201331.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2827036"},{"key":"e_1_2_1_61_1","volume-title":"Proceeding of the International Conference on Machine Learning. 11523\u201311533","author":"Zhou Tianyi","year":"2020","unstructured":"Tianyi Zhou , Shengjie Wang , and Jeff Bilmes . 2020 . Time-consistent self-supervision for semi-supervised learning . In Proceeding of the International Conference on Machine Learning. 11523\u201311533 . Tianyi Zhou, Shengjie Wang, and Jeff Bilmes. 2020. Time-consistent self-supervision for semi-supervised learning. In Proceeding of the International Conference on Machine Learning. 11523\u201311533."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/3041838.3041953"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3451884","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3451884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:59Z","timestamp":1750197779000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3451884"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,20]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3451884"],"URL":"https:\/\/doi.org\/10.1145\/3451884","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,20]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}