{"url":"/task/multi-label-learning","name":"Multi-Label Learning","slug":"multi-label-learning","description_markdown":"Multi-label learning (MLL) is a generalization of the binary and multi-category classification problems and deals with tagging a data instance with several possible class labels simultaneously [1]. Each of the assigned labels conveys a specific semantic relationship with the multi-label data instance [2, 3]. Multi-label learning has continued to receive a lot of research interest due to its practical application in many real-world problems such as recommender systems [4], image annotation [5], and text classification [6].\r\n\r\nReferences: \r\n\r\n1. Kumar, S., Rastogi, R., Low rank label subspace transformation for multi-label learning with missing labels. Information Sciences 596, 53–72 (2022)\r\n\r\n2. Zhang M-L, Zhou Z-H (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837\r\n\r\n3. Gibaja E, Ventura S (2015) A tutorial on multilabel learning. ACM Comput Surveys (CSUR) 47(3):1–38\r\n\r\n4. Bogaert M, Lootens J, Van den Poel D, Ballings M (2019) Evaluating multi-label classifiers and recommender systems in the financial service sector. Eur J Oper Res 279(2):620– 634\r\n\r\n5. Jing L, Shen C, Yang L, Yu J, Ng MK (2017) Multi-label classification by semi-supervised singular value decomposition. IEEE Trans Image Process 26(10):4612–4625\r\n\r\n6. Chen Z, Ren J (2021) Multi-label text classification with latent word-wise label information. Appl Intell 51(2):966–979","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":299,"papers_with_code":92,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/multi-label-learning-on-coco-2014","slug":"multi-label-learning-on-coco-2014","dataset":"COCO 2014","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["CF1","CP","CR","OF1","OP","OR","mAP"],"first_row_in_archive_order":{"model":"SADCL","paper_title":"Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification","paper_url":"/paper/semantic-aware-dual-contrastive-learning-for","paper_date":"2023-07-19","arxiv_id":"2307.09715","code_links":[{"title":"yu-gi-oh-leilei/sadcl","url":"https://github.com/yu-gi-oh-leilei/sadcl"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/expw","name":"ExpW","full_name":"Expression in-the-Wild","num_papers_in_archive":41},{"url":"/dataset/birdsong","name":"BirdSong","full_name":"","num_papers_in_archive":35},{"url":"/dataset/animal-kingdom","name":"Animal Kingdom","full_name":"","num_papers_in_archive":26},{"url":"/dataset/extreme-classification","name":"EXTREME CLASSIFICATION","full_name":"Extreme Multi-label Classification","num_papers_in_archive":18},{"url":"/dataset/multi-label-classification-dataset-repository","name":"Multi-Label Classification Dataset Repository","full_name":"Multi-Label Classification Dataset Repository","num_papers_in_archive":4},{"url":"/dataset/corn-seeds-dataset","name":"Corn Seeds Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/mimic-meme-dataset","name":"MIMIC Meme Dataset","full_name":"Misogyny Identification in Multimodal Internet Content in Hindi-English Code-Mix Language","num_papers_in_archive":0}],"subtasks":[{"url":"/task/missing-labels","name":"Missing Labels"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":92,"tagged_in_all":299,"items":[{"url":"/paper/training-deep-networks-for-facial-expression","title":"Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution","date":"2016-08-03","arxiv_id":"1608.01041","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/a-survey-on-extreme-multi-label-learning","title":"A Survey on Extreme Multi-label Learning","date":"2022-10-08","arxiv_id":"2210.03968","repositories_listed":4,"syntology":null},{"url":"/paper/mer-2023-multi-label-learning-modality","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","date":"2023-04-18","arxiv_id":"2304.08981","repositories_listed":3,"syntology":null},{"url":"/paper/bonsai-diverse-and-shallow-trees-for-extreme","title":"Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification","date":"2019-04-17","arxiv_id":"1904.08249","repositories_listed":3,"syntology":null},{"url":"/paper/mer-2024-semi-supervised-learning-noise","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","date":"2024-04-26","arxiv_id":"2404.17113","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/dicnet-deep-instance-level-contrastive","title":"DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification","date":"2023-03-15","arxiv_id":"2303.08358","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/cement-incomplete-multi-view-weak-label","title":"Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels","date":"2022-01-04","arxiv_id":"2201.01079","repositories_listed":2,"syntology":null},{"url":"/paper/simple-and-robust-loss-design-for-multi-label","title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels","date":"2021-12-13","arxiv_id":"2112.07368","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/multi-label-learning-from-single-positive","title":"Multi-Label Learning from Single Positive Labels","date":"2021-06-17","arxiv_id":"2106.09708","repositories_listed":2,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/multi-moments-in-time-learning-and","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","date":"2019-11-01","arxiv_id":"1911.00232","repositories_listed":2,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":10}},{"url":"/paper/self-paced-multi-label-learning-with","title":"Self-Paced Multi-Label Learning with Diversity","date":"2019-10-08","arxiv_id":"1910.03497","repositories_listed":2,"syntology":null},{"url":"/paper/synthetic-oversampling-of-multi-label-data","title":"Synthetic Oversampling of Multi-Label Data based on Local Label Distribution","date":"2019-05-02","arxiv_id":"1905.00609","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-separate-object-sounds-by","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","date":"2018-04-05","arxiv_id":"1804.01665","repositories_listed":2,"syntology":null},{"url":"/paper/food-ingredients-recognition-through-multi","title":"Food Ingredients Recognition through Multi-label Learning","date":"2017-07-27","arxiv_id":"1707.08816","repositories_listed":2,"syntology":null},{"url":"/paper/dismec-distributed-sparse-machines-for","title":"DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification","date":"2016-09-08","arxiv_id":"1609.02521","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/deep-region-and-multi-label-learning-for","title":"Deep Region and Multi-Label Learning for Facial Action Unit Detection","date":"2016-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/cut-out-and-replay-a-simple-yet-versatile","title":"Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning","date":"2025-05-26","arxiv_id":"2505.19680","repositories_listed":1,"syntology":null},{"url":"/paper/protoecgnet-case-based-interpretable-deep","title":"ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning","date":"2025-04-11","arxiv_id":"2504.08713","repositories_listed":1,"syntology":null},{"url":"/paper/label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-but-effective-closed-form-solution","title":"A Simple but Effective Closed-form Solution for Extreme Multi-label Learning","date":"2025-01-17","arxiv_id":"2501.10179","repositories_listed":1,"syntology":null},{"url":"/paper/towards-macro-auc-oriented-imbalanced-multi","title":"Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning","date":"2024-12-24","arxiv_id":"2412.18231","repositories_listed":1,"syntology":null},{"url":"/paper/dual-decoupling-learning-and-metric-adaptive","title":"Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning","date":"2024-07-26","arxiv_id":"2407.18624","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-learning-with-random-circular","title":"Multi-label Learning with Random Circular Vectors","date":"2024-07-08","arxiv_id":"2407.05656","repositories_listed":1,"syntology":null},{"url":"/paper/pedestrian-attribute-recognition-as-label","title":"Pedestrian Attribute Recognition as Label-balanced Multi-label Learning","date":"2024-05-08","arxiv_id":"2405.04858","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-single-positive-multi-label","title":"Boosting Single Positive Multi-label Classification with Generalized Robust Loss","date":"2024-05-06","arxiv_id":"2405.03501","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/propml-probability-partial-multi-label","title":"ProPML: Probability Partial Multi-label Learning","date":"2024-03-12","arxiv_id":"2403.07603","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/miml-library-a-modular-and-flexible-library","title":"MIML library: a Modular and Flexible Library for Multi-instance Multi-label Learning","date":"2024-02-12","arxiv_id":"2402.08056","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-pseudo-labels-for-single","title":"Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning","date":"2023-10-24","arxiv_id":"2310.15985","repositories_listed":1,"syntology":null},{"url":"/paper/neural-collapse-in-multi-label-learning-with","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","date":"2023-10-24","arxiv_id":"2310.15903","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}},{"url":"/paper/multi-label-feature-selection-using-adaptive","title":"Multi-Label Feature Selection Using Adaptive and Transformed Relevance","date":"2023-09-26","arxiv_id":"2309.14768","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}