{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:20:49Z","timestamp":1761402049292,"version":"3.41.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2020,2,9]],"date-time":"2020-02-09T00:00:00Z","timestamp":1581206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"crossref","award":["IIS-1763452 and CNS-1828181"],"award-info":[{"award-number":["IIS-1763452 and CNS-1828181"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2020,4,30]]},"abstract":"<jats:p>Long Short-Term Memory (LSTM) network, a popular deep-learning model, is particularly useful for data with temporal correlation, such as texts, sequences, or time series data, thanks to its well-sought after recurrent network structures designed to capture temporal correlation. In this article, we propose to generalize LSTM to generic machine-learning tasks where data used for training do not have explicit temporal or sequential correlation. Our theme is to explore feature correlation in the original data and convert each instance into a synthetic sentence format by using a two-gram probabilistic language model. More specifically, for each instance represented in the original feature space, our conversion first seeks to horizontally align original features into a sequentially correlated feature vector, resembling to the letter coherence within a word. In addition, a vertical alignment is also carried out to create multiple time points and simulate word sequential order in a sentence (<jats:italic>i.e.,<\/jats:italic>word correlation). The two dimensional horizontal-and-vertical alignments not only ensure feature correlations are maximally utilized, but also preserve the original feature values in the new representation. As a result, LSTM model can be utilized to achieve good classification accuracy, even if the underlying data do not have temporal or sequential dependency. Experiments on 20 generic datasets show that applying LSTM to generic data can improve the classification accuracy, compared to conventional machine-learning methods. This research opens a new opportunity for LSTM deep learning to be broadly applied to generic machine-learning tasks.<\/jats:p>","DOI":"10.1145\/3366022","type":"journal-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T06:49:13Z","timestamp":1581317353000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Generalizing Long Short-Term Memory Network for Deep Learning from Generic Data"],"prefix":"10.1145","volume":"14","author":[{"given":"Huimei","family":"Han","sequence":"first","affiliation":[{"name":"Zhejiang University of Technology and Florida Atlantic University, Zhejiang, P.R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4129-9611","authenticated-orcid":false,"given":"Xingquan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Florida Atlantic University, Boca Raton, FL"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Shannxi, P.R. China"}]}],"member":"320","published-online":{"date-parts":[[2020,2,9]]},"reference":[{"volume-title":"Tensorflow: Large-scale machine learning on heterogeneous systems. 1","year":"2015","author":"Abadi M.","key":"e_1_2_1_1_1"},{"volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. 258--267","author":"Adam Pauls A.","key":"e_1_2_1_2_1"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/25.775362"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2005.06.007"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2013.50"},{"volume-title":"Proceedings of the Advances in Neural Information Processing Systems, British Columbia, Canada","author":"Bengio Y.","key":"e_1_2_1_6_1"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Mairead L. Bermingham Ricardo Pong-Wong Athina Spiliopoulou etal 2015. Application of high-dimensional feature selection: Evaluation for genomic prediction in man. Scientific Reports 5 10312 (2015). Mairead L. Bermingham Ricardo Pong-Wong Athina Spiliopoulou et al. 2015. Application of high-dimensional feature selection: Evaluation for genomic prediction in man. Scientific Reports 5 10312 (2015).","DOI":"10.1038\/srep10312"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00063-5"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022607123649"},{"volume-title":"Convex sparse PCA for unsupervised feature learning. ACM Transactions on Knowledge Discovery from Data 11, 1","year":"2016","author":"Chang Xiaojun","key":"e_1_2_1_11_1"},{"key":"e_1_2_1_12_1","doi-asserted-by":"crossref","unstructured":"L. Changki and L. G. Geunbae. 2006. Information gain and divergence-based feature selection for machine learning-based text categorization. Information Processing 8 Management 42 1 (2006) 155--165. L. Changki and L. G. Geunbae. 2006. Information gain and divergence-based feature selection for machine learning-based text categorization. Information Processing 8 Management 42 1 (2006) 155--165.","DOI":"10.1016\/j.ipm.2004.08.006"},{"volume-title":"Proceedings of the Conference on Knowledge Discovery and Data Mining.","author":"Chen T.","key":"e_1_2_1_13_1"},{"key":"e_1_2_1_14_1","unstructured":"Yanping Chen Eamonn Keogh Bing Hu Nurjahan Begum Anthony Bagnall Abdullah Mueen and Gustavo Batista. 2015. The UCR Time Series Classification Archive. Retrieved from www.cs.ucr.edu\/&sim;eamonn\/time_series_data\/. Yanping Chen Eamonn Keogh Bing Hu Nurjahan Begum Anthony Bagnall Abdullah Mueen and Gustavo Batista. 2015. The UCR Time Series Classification Archive. Retrieved from www.cs.ucr.edu\/&sim;eamonn\/time_series_data\/."},{"volume-title":"Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. 3642--3649","author":"Ciresan Dan","key":"e_1_2_1_15_1"},{"volume-title":"Neural Networks for Pattern Recognition","author":"Bishop C. M.","key":"e_1_2_1_16_1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"volume-title":"Proceedings of the 8th Australian Conference on Neural Networks. 181--185","author":"Dunne R. A.","key":"e_1_2_1_18_1"},{"volume-title":"Proceedings of the Second Workshop on Statistical Machine Translation. 88--95","author":"Federico M.","key":"e_1_2_1_19_1"},{"key":"e_1_2_1_20_1","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"Gers F.","year":"2002","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Deep Learning","author":"Goodfellow Ian","key":"e_1_2_1_21_1"},{"volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. 6645--6649","author":"Graves A.","key":"e_1_2_1_22_1"},{"volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Graves A.","key":"e_1_2_1_23_1"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944968"},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"M. F. A. Hady and F. Schwenker. 2013. Semi-supervised Learning in Handbook on Neural Information Processing. Springer Berlin Germany. M. F. A. Hady and F. Schwenker. 2013. Semi-supervised Learning in Handbook on Neural Information Processing. Springer Berlin Germany.","DOI":"10.1007\/978-3-642-36657-4_7"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.10.053"},{"volume-title":"Proceedings of the IEEE International Conference on Data Mining.","author":"Han H.","key":"e_1_2_1_28_1"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.2478\/v10117-011-0021-1"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"volume-title":"An Introduction to Statistical Learning","author":"James Gareth","key":"e_1_2_1_32_1"},{"volume-title":"Proceedings of the 12th International Conference on Semantic Systems.","year":"2016","author":"John Adebayo Kolawole","key":"e_1_2_1_33_1"},{"volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Kingma D.","key":"e_1_2_1_34_1"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00043-X"},{"volume-title":"Proceedings of the 26th Annual Conference on Neural Information Processing Systems","year":"2012","author":"Krizhevsky Alex","key":"e_1_2_1_36_1"},{"key":"e_1_2_1_37_1","first-page":"1787","article-title":"Feature selection methods and algorithms","volume":"3","author":"Ladla L.","year":"2011","journal-title":"International Journal on Computer Science and Engineering"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA292575"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2916726"},{"volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"LeCun Y.","key":"e_1_2_1_41_1"},{"volume-title":"Feature Extraction, Construction and Selection: A Data Mining Perspective","author":"Liu Huan","key":"e_1_2_1_42_1"},{"volume-title":"Proceedings of the 7th IEEE International Conference on Tools with Artificial Intelligence.","author":"Liu H.","key":"e_1_2_1_43_1"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2279894"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.2819119"},{"key":"e_1_2_1_46_1","unstructured":"D. Newman S. Hettich C. Blake and C. Merz. 1998. UCI repository of machine learning databases Irvine. University of California Department of Information and Computer Science CA. Retrieved from http:\/\/www.ics.uci.edu\/&sim;mlearn\/MLRepository.html. D. Newman S. Hettich C. Blake and C. Merz. 1998. UCI repository of machine learning databases Irvine. University of California Department of Information and Computer Science CA. Retrieved from http:\/\/www.ics.uci.edu\/&sim;mlearn\/MLRepository.html."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/1899353.1899359"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"volume-title":"Neural Networks for Signal Processing","author":"Scholkopft B.","key":"e_1_2_1_51_1"},{"key":"e_1_2_1_52_1","first-page":"2579","article-title":"Visualizing High-dimensional data using t-SNE","volume":"9","author":"van der Maaten L. J. P.","year":"2008","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Proceedings of the Conference on Conference on Empirical Methods in Natural Language Processing.","author":"Wang Y.","key":"e_1_2_1_53_1"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00075"},{"key":"e_1_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Y. Wu S. Hio T. Mei and N. Yu. 2017. Large-scale online feature selection for ultra-high dimensional sparse data. ACM Transactions on Knowledge Discovery from Data 11 4 (2017) 48:1--48:22. Y. Wu S. Hio T. Mei and N. Yu. 2017. Large-scale online feature selection for ultra-high dimensional sparse data. ACM Transactions on Knowledge Discovery from Data 11 4 (2017) 48:1--48:22.","DOI":"10.1145\/3070646"},{"volume-title":"Scalable and accurate online feature selection for big data. ACM Transactions on Knowledge Discovery from Data 11, 2","year":"2016","author":"Yu Kui","key":"e_1_2_1_56_1"},{"volume-title":"Proceedings of the SIAM International Conference on Data Mining","author":"Zhang D.","key":"e_1_2_1_57_1"},{"volume-title":"Network representation learning: A survey","year":"2018","author":"Zhang Daokun","key":"e_1_2_1_58_1"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2157999"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366022","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:08Z","timestamp":1750268948000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,9]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,4,30]]}},"alternative-id":["10.1145\/3366022"],"URL":"https:\/\/doi.org\/10.1145\/3366022","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2020,2,9]]},"assertion":[{"value":"2018-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-02-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}