{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T21:50:32Z","timestamp":1776203432762,"version":"3.50.1"},"reference-count":76,"publisher":"Association for Computing Machinery (ACM)","issue":"7","funder":[{"name":"Jiangsu Science Foundation","award":["BK20243012, BG2024036"],"award-info":[{"award-number":["BK20243012, BG2024036"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62125602, U24A20324, 92464301, 62206050, 62206052"],"award-info":[{"award-number":["62125602, U24A20324, 92464301, 62206050, 62206052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2242025K30024, B250201040, aiia-25-01, aiia-25-03"],"award-info":[{"award-number":["2242025K30024, B250201040, aiia-25-01, aiia-25-03"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2024M750424"],"award-info":[{"award-number":["2024M750424"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20240252"],"award-info":[{"award-number":["GZC20240252"]}]},{"name":"Jiangsu Funding Program for Excellent Postdoctoral Talent","award":["2024ZB242"],"award-info":[{"award-number":["2024ZB242"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>\n            Multi-Label Learning (MLL) involves the task of assigning a set of relevant labels to a given instance. Recently,\n            <jats:italic toggle=\"yes\">Label Enhancement<\/jats:italic>\n            (LE) has gained significant attention in various MLL tasks, as it allows for effective mining the implicit relative importance information of different labels. However, in existing LE-based MLL methods, the LE process is decoupled from the MLL process. Consequently, the label distribution recovered by the LE process may not be suitable for training the predictive model, thus affecting the overall learning system. In this study, we propose a novel approach named\n            <jats:italic toggle=\"yes\">interactive Fusion Label Enhancement for Multi-Label Learning<\/jats:italic>\n            (\n            <jats:sc>Flem<\/jats:sc>\n            ) that seamlessly integrates the LE process with the MLL process. Specifically, we introduce a matching and interaction mechanism comprising a novel interaction label enhancement loss and a contrastive alignment approach to prevent object mismatch. Furthermore, we present a unified label distribution loss that establishes the relationship between the recovered label distribution and the training of the predictive model. By leveraging these losses, the label distributions obtained from the LE process can be efficiently utilized for training the predictive model. Experimental results on multiple benchmark datasets demonstrate the effectiveness of the proposed method.\n          <\/jats:p>","DOI":"10.1145\/3744571","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T10:26:51Z","timestamp":1749724011000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Interactive Fusion Label Enhancement for Multi-Label Learning"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6541-3445","authenticated-orcid":false,"given":"Xingyu","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China and 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":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China and 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 and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7091-0702","authenticated-orcid":false,"given":"Lei","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, 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 and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3388094"},{"key":"e_1_3_1_3_2","first-page":"1383","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"162","author":"Bai Junwen","year":"2022","unstructured":"Junwen Bai, Shufeng Kong, and Carla P. Gomes. 2022. Gaussian mixture variational autoencoder with contrastive learning for multi-label classification. In Proceedings of the International Conference on Machine Learning, Vol. 162, 1383\u20131398."},{"key":"e_1_3_1_4_2","first-page":"730","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Bhatia Kush","year":"2015","unstructured":"Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain. 2015. Sparse local embeddings for extreme multi-label classification. In Proceedings of the Annual Conference on Neural Information Processing Systems, 730\u2013738."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.009"},{"issue":"1","key":"e_1_3_1_6_2","first-page":"1","article-title":"Une in\u00e9galit\u00e9","volume":"25","author":"Carlson F.","year":"1934","unstructured":"F. Carlson. 1934. Une in\u00e9galit\u00e9. Archive for Mathematics, Astronomy and Physics 25B, 1 (1934), 1\u20135.","journal-title":"Archive for Mathematics, Astronomy and Physics"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29725"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_1_10_2","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","author":"Cui Yin","year":"2019","unstructured":"Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge J. Belongie. 2019. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9268\u20139277.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_1_12_2","first-page":"681","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Elisseeff Andr\u00e9","year":"2001","unstructured":"Andr\u00e9 Elisseeff and Jason Weston. 2001. A kernel method for multi-labelled classification. In Proceedings of the Annual Conference on Neural Information Processing Systems, 681\u2013687."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5064-8"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/446"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2545658"},{"key":"e_1_3_1_16_2","first-page":"4944","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Guo Chuan","year":"2019","unstructured":"Chuan Guo, Ali Mousavi, Xiang Wu, Daniel Niels Holtmann-Rice, Satyen Kale, Sashank J. Reddi, and Sanjiv Kumar. 2019. Breaking the glass ceiling for embedding-based classifiers for large output spaces. In Proceedings of the Annual Conference on Neural Information Processing Systems, 4944\u20134954."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013747"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103224"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10258"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.643"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02418571"},{"issue":"2","key":"e_1_3_1_23_2","first-page":"1708","article-title":"Label enhancement by maintaining positive and negative label relation","volume":"35","author":"Jia Xiuyi","year":"2023","unstructured":"Xiuyi Jia, Yunan Lu, and Fangwen Zhang. 2023. Label enhancement by maintaining positive and negative label relation. IEEE Transactions on Knowledge and Data Engineering 35, 2 (2023), 1708\u20131720.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_24_2","first-page":"793","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Kakade Sham M.","year":"2008","unstructured":"Sham M. Kakade, Karthik Sridharan, and Ambuj Tewari. 2008. On the complexity of linear prediction: Risk bounds, margin bounds, and regularization. In Proceedings of the Annual Conference on Neural Information Processing Systems, 793\u2013800."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05888-2"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01986"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25244"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462454"},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1109\/TMM.2011.2129498","article-title":"Cost-sensitive multi-label learning for audio tag annotation and retrieval","volume":"13","author":"Lo Hung-Yi","year":"2011","unstructured":"Hung-Yi Lo, Ju-Chiang Wang, Hsin-Min Wang, and Shou-De Lin. 2011. Cost-sensitive multi-label learning for audio tag annotation and retrieval. IEEE Transactions on Multimedia 13, 3 (2011), 518\u2013529.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_1_32_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3537900"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3372693"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103075"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_1"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3204219"},{"key":"e_1_3_1_38_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Reddi Sashank J.","year":"2018","unstructured":"Sashank J. Reddi, Satyen Kale, and Sanjiv Kumar. 2018. On the convergence of Adam and beyond. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-0611-6"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00059"},{"key":"e_1_3_1_42_2","unstructured":"Jianlin Su Mingren Zhu Ahmed Murtadha Shengfeng Pan Bo Wen and Yunfeng Liu. 2022. ZLPR: A novel loss for multi-label classification. arXiv:2208.02955. Retrieved from https:\/\/arxiv.org\/abs\/2208.02955"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097987"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3054465"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29447"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-41055-9"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1289"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/343"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643853"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015256"},{"issue":"9","key":"e_1_3_1_52_2","first-page":"5445","article-title":"Re-weighting large margin label distribution learning for classification","volume":"44","author":"Wang Jing","year":"2022","unstructured":"Jing Wang, Xin Geng, and Hui Xue. 2022. Re-weighting large margin label distribution learning for classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2022), 5445\u20135459.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"e_1_3_1_53_2","first-page":"1502","article-title":"Fast label enhancement for label distribution learning","volume":"35","author":"Wang Ke","year":"2023","unstructured":"Ke Wang, Ning Xu, Miaogen Ling, and Xin Geng. 2023. Fast label enhancement for label distribution learning. IEEE Transactions on Knowledge and Data Engineering 35, 2 (2023), 1502\u20131514.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288205"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2947040"},{"key":"e_1_3_1_57_2","first-page":"27119","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Xu Ning","year":"2021","unstructured":"Ning Xu, Congyu Qiao, Xin Geng, and Min-Ling Zhang. 2021. Instance-dependent partial label learning. In Proceedings of the Annual Conference on Neural Information Processing Systems, 27119\u201327130."},{"key":"e_1_3_1_58_2","first-page":"10597","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xu Ning","year":"2020","unstructured":"Ning Xu, Jun Shu, Yun-Peng Liu, and Xin Geng. 2020. Variational label enhancement. In Proceedings of the International Conference on Machine Learning, 10597\u201310606."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597416"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-017-7031-7"},{"key":"e_1_3_1_61_2","first-page":"2057","article-title":"Leveraging implicit relative labeling-importance information for effective multi-label learning","author":"Zhang Min-Ling","year":"2021","unstructured":"Min-Ling Zhang, Qian-Wen Zhang, Jun-Peng Fang, Yu-Kun Li, and Xin Geng. 2021. Leveraging implicit relative labeling-importance information for effective multi-label learning. IEEE Transactions on Knowledge and Data Engineering (2021), 2057\u20132070.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/551"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29619"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40192-5"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532190"},{"key":"e_1_3_1_68_2","article-title":"Scalable label distribution learning for multi-label classification","author":"Zhao Xingyu","year":"2024","unstructured":"Xingyu Zhao, Yuexuan An, Lei Qi, and Xin Geng. 2024. Scalable label distribution learning for multi-label classification. IEEE Transactions on Neural Networks and Learning Systems (2024).","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/524"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109056"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3323401"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26341"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611693"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539311"},{"issue":"1","key":"e_1_3_1_75_2","first-page":"482","article-title":"Generalized label enhancement with sample correlations","volume":"35","author":"Zheng Qinghai","year":"2023","unstructured":"Qinghai Zheng, Jihua Zhu, Haoyu Tang, Xinyuan Liu, Zhongyu Li, and Huimin Lu. 2023. Generalized label enhancement with sample correlations. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2023), 482\u2013495.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284812"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3744571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T08:08:44Z","timestamp":1755850124000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":76,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3744571"],"URL":"https:\/\/doi.org\/10.1145\/3744571","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"2024-08-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}