{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:47:44Z","timestamp":1776880064940,"version":"3.51.2"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2018AAA0100104"],"award-info":[{"award-number":["2018AAA0100104"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125602"],"award-info":[{"award-number":["62125602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076063"],"award-info":[{"award-number":["62076063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206050"],"award-info":[{"award-number":["62206050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M700023"],"award-info":[{"award-number":["2021M700023"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Science Foundation for Youths","award":["BK20210220"],"award-info":[{"award-number":["BK20210220"]}]},{"DOI":"10.13039\/501100017547","name":"Jiangsu Association for Science and Technology","doi-asserted-by":"publisher","award":["TJ-2022-078"],"award-info":[{"award-number":["TJ-2022-078"]}],"id":[{"id":"10.13039\/501100017547","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tkde.2023.3323401","type":"journal-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T19:31:54Z","timestamp":1696966314000},"page":"2716-2729","source":"Crossref","is-referenced-by-count":22,"title":["Variational Continuous Label Distribution Learning for Multi-Label Text Classification"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6541-3445","authenticated-orcid":false,"given":"Xingyu","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5510-4059","authenticated-orcid":false,"given":"Yuexuan","family":"An","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8336-5926","authenticated-orcid":false,"given":"Ning","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-0622","authenticated-orcid":false,"given":"Xin","family":"Geng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1531-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2154-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2716262"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1063"},{"key":"ref9","first-page":"2873","article-title":"Recurrent neural network for text classification with multi-task learning","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Liu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"ref12","first-page":"5413","article-title":"Maximizing subset accuracy with recurrent neural networks in multi-label classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nam"},{"key":"ref13","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Yang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1485"},{"key":"ref15","first-page":"5812","article-title":"AttentionXML: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref20","first-page":"10809","article-title":"Pretrained generalized autoregressive model with adaptive probabilistic label clusters for extreme multi-label text classification","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403368"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016359"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00259"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403151"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8928"},{"key":"ref30","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488391"},{"key":"ref34","article-title":"LSHTC: A benchmark for large-scale text classification","author":"Partalas","year":"2015"},{"key":"ref35","first-page":"13244","article-title":"Extreme classification in log memory using count-min sketch: A case study of amazon search with 50m products","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Medini"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441807"},{"key":"ref37","first-page":"4944","article-title":"Breaking the glass ceiling for embedding-based classifiers for large output spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.75"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512174"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz142"},{"key":"ref42","article-title":"X-BERT: Extreme multi-label text classification with BERT","author":"Chang","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1289"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2002-6504"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"ref49","first-page":"872","article-title":"What is the effect of importance weighting in deep learning?","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Byrd"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00677"},{"key":"ref54","first-page":"950","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krogh"},{"key":"ref55","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2545658"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109056"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26341"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015256"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/406"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3203678"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/524"},{"key":"ref63","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref64","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref65","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref66","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref67","first-page":"2866","article-title":"Learning hierarchical priors in VAEs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Klushyn"},{"key":"ref68","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"S\u00f8nderby"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00030"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.643"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_4"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20147"},{"key":"ref73","article-title":"Enhancing navigation on Wikipedia with social tags","author":"Zubiaga","year":"2012"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312647"},{"key":"ref75","first-page":"730","article-title":"Sparse local embeddings for extreme multi-label classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bhatia"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref77","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref78","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939756"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10506969\/10275121.pdf?arnumber=10275121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T22:25:22Z","timestamp":1715120722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10275121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2023.3323401","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}