{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T04:37:49Z","timestamp":1771043869827,"version":"3.50.1"},"reference-count":68,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20230091, GZB20230092"],"award-info":[{"award-number":["GZB20230091, GZB20230092"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2023MD744127, 2023M740383"],"award-info":[{"award-number":["2023MD744127, 2023M740383"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"crossref","award":["24NSFSC1654"],"award-info":[{"award-number":["24NSFSC1654"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"crossref"}]},{"name":"School Talent Introduction Program","award":["Z222066"],"award-info":[{"award-number":["Z222066"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2024,10,31]]},"abstract":"<jats:p>Representation learning is an important topic in machine learning, pattern recognition, and data mining research. Among many representation learning approaches, semi-nonnegative matrix factorization (SNMF) is a frequently-used one. However, a typical problem of SNMF is that usually there is no learning rate guidance during the optimization process, which often leads to a poor representation ability. To overcome this limitation, we propose a very general representation learning framework (DNSRF) that is based on a deep neural net. Essentially, the parameters of the deep net used to construct the DNSRF algorithms are obtained by matrix element update. In combination with different activation functions, DNSRF can be implemented in various ways. In our experiments, we tested nine instances of our DNSRF framework on six benchmark datasets. In comparison with other state-of-the-art methods, the results demonstrate the superior performance of our framework, which is thus shown to have a great representation ability.<\/jats:p>","DOI":"10.1145\/3670408","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T14:26:40Z","timestamp":1717424800000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["DNSRF: Deep Network-based Semi-NMF Representation Framework"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-1023","authenticated-orcid":false,"given":"Dexian","family":"Wang","sequence":"first","affiliation":[{"name":"Chengdu University of Traditional Chinese Medicine, Southwest Jiaotong University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7780-104X","authenticated-orcid":false,"given":"Tianrui","family":"Li","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7208-8855","authenticated-orcid":false,"given":"Ping","family":"Deng","sequence":"additional","affiliation":[{"name":"Xihua University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4053-5443","authenticated-orcid":false,"given":"Zhipeng","family":"Luo","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7090-0325","authenticated-orcid":false,"given":"Pengfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chengdu University of Traditional Chinese Medicine, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-6284","authenticated-orcid":false,"given":"Keyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-107X","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2606098"},{"key":"e_1_3_1_4_2","first-page":"695","volume-title":"Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS \u201912)","author":"Alshabrawy Ossama S.","year":"2012","unstructured":"Ossama S. Alshabrawy, Mohamed Elsayed Ghoneim, Wael Awad, and Aboul Ella Hassanien. 2012. Underdetermined blind source separation based on fuzzy c-means and semi-nonnegative matrix factorization. In Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS \u201912). IEEE, 695\u2013700."},{"key":"e_1_3_1_5_2","volume-title":"Singular Value Decomposition Tutorial","author":"Baker Kirk","year":"2005","unstructured":"Kirk Baker. 2005. Singular Value Decomposition Tutorial, Vol. 24. The Ohio State University."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Peter W. Battaglia Jessica B. Hamrick Victor Bapst Alvaro Sanchez-Gonzalez Vinicius Zambaldi Mateusz Malinowski Andrea Tacchetti David Raposo Adam Santoro Ryan Faulkner Caglar Gulcehre Francis Song Andrew Ballard Justin Gilmer George Dahl Ashish Vaswani Kelsey Allen Charles Nash Victoria Langston Chris Dyer Nicolas Heess Daan Wierstra Pushmeet Kohli Matt Botvinick Oriol Vinyals Yujia Li and Razvan Pascanu. 2018. Relational inductive biases deep learning and graph networks. arXiv:1806.01261. Retrieved from 10.48550\/arXiv.1806.01261","DOI":"10.48550\/arXiv.1806.01261"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"issue":"8","key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1109\/TPAMI.2010.231","article-title":"Graph regularized nonnegative matrix factorization for data representation","volume":"33","author":"Cai Deng","year":"2010","unstructured":"Deng Cai, Xiaofei He, Jiawei Han, and Thomas S. Huang. 2010. Graph regularized nonnegative matrix factorization for data representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 8 (2010), 1548\u20131560.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"e_1_3_1_10_2","first-page":"6930","article-title":"Fast flexible bipartite graph model for co-clustering","volume":"35","author":"Chen Wei","year":"2022","unstructured":"Wei Chen, Hongjun Wang, Zhiguo Long, and Tianrui Li. 2022. Fast flexible bipartite graph model for co-clustering. IEEE Transactions on Knowledge and Data Engineering 35, 7 (2022), 6930\u20136940.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2775220"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2016.6.4.603"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110425"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3154030"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.036"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.70"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.277"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107736"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2448542"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.070"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3266595"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"e_1_3_1_23_2","first-page":"19","volume-title":"A Tutorial Overview of Vector and Matrix Norms","author":"Kahan William","year":"2013","unstructured":"William Kahan. 2013. A Tutorial Overview of Vector and Matrix Norms. University of California, Berkeley, CA, Lecture Notes, 19."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114805"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-017-0883-0"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2400461"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646051"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.11.008"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_30"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Behnam Neyshabur Ryota Tomioka and Nathan Srebro. 2014. In search of the real inductive bias: On the role of implicit regularization in deep learning. arXiv:1412.6614. Retrieved from 10.48550\/arXiv.1412.6614","DOI":"10.48550\/arXiv.1412.6614"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2022.9020048"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.12.098"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107683"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.021"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.12.046"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1177\/0954406219827332"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2811910"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133157"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10882-x"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09766-w"},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3159998","article-title":"Bi-endmember semi-NMF based on low-rank and sparse matrix decomposition","volume":"60","author":"Song Meiping","year":"2022","unstructured":"Meiping Song, Tingting Yang, Hongju Cao, Fang Li, Bai Xue, Sen Li, and Chein-I. Chang. 2022. Bi-endmember semi-NMF based on low-rank and sparse matrix decomposition. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1\u201316.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-170729"},{"key":"e_1_3_1_46_2","first-page":"1692","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Trigeorgis George","year":"2014","unstructured":"George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, and Bjoern Schuller. 2014. A deep semi-NMF model for learning hidden representations. In Proceedings of the International Conference on Machine Learning. PMLR, 1692\u20131700."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3163584"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.05.101"},{"issue":"7","key":"e_1_3_1_49_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3584862","article-title":"A generalized deep learning clustering algorithm based on non-negative matrix factorization","volume":"17","author":"Wang Dexian","year":"2023","unstructured":"Dexian Wang, Tianrui Li, Ping Deng, Fan Zhang, Wei Huang, Pengfei Zhang, and Jia Liu. 2023a. A generalized deep learning clustering algorithm based on non-negative matrix factorization. ACM Transactions on Knowledge Discovery from Data 17, 7 (2023), 1\u201320.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101884"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2747400"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.06.013"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3010332"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009029"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3031666"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109152"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271697"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944869"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109274"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2251349"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3114734"},{"key":"e_1_3_1_62_2","first-page":"1126","volume-title":"Proceedings of the 8th International Conference on Digital Image Processing (ICDIP \u201916)","volume":"10033","author":"Zeng Xianhua","year":"2016","unstructured":"Xianhua Zeng, Shengwei Qu, and Zhilong Wu. 2016. Graph regularized deep semi-nonnegative matrix factorization for clustering. In Proceedings of the 8th International Conference on Digital Image Processing (ICDIP \u201916), Vol. 10033. 1126\u20131130."},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164190"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.11.004"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.12.027"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01524-1"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893956"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102534"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2017.05.001"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670408","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3670408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:38Z","timestamp":1750291538000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"references-count":68,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10,31]]}},"alternative-id":["10.1145\/3670408"],"URL":"https:\/\/doi.org\/10.1145\/3670408","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"2022-11-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}