{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/hierarchical-multi-label-classification","title":"Hierarchical Multi-Label Classification Networks","arxiv_id":null,"date":"2018-07-01","proceeding":"ICML 2018 7","authors":["Jonatas Wehrmann","Ricardo Cerri","Rodrigo Barros"],"abstract":"\n    One of the most challenging machine learning problems is a particular case of data classification in which classes are hierarchically structured and objects can be assigned to multiple paths of the class hierarchy at the same time. This task is known as hierarchical multi-label classification (HMC), with applications in text classification, image annotation, and in bioinformatics problems such as protein function prediction. In this paper, we propose novel neural network architectures for HMC called HMCN, capable of simultaneously optimizing local and global loss functions for discovering local hierarchical class-relationships and global information from the entire class hierarchy while penalizing hierarchical violations. We evaluate its performance in 21 datasets from four distinct domains, and we compare it against the current HMC state-of-the-art approaches. Results show that HMCN substantially outperforms all baselines with statistical significance, arising as the novel state-of-the-art for HMC.\n  ","url_abs":"https://icml.cc/Conferences/2018/Schedule?showEvent=2306","url_pdf":"http://proceedings.mlr.press/v80/wehrmann18a/wehrmann18a.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"hierarchical-multi-label-classification","task_name":"Hierarchical Multi-label Classification"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"protein-function-prediction","task_name":"Protein Function Prediction"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hierarchical-multi-label-classification-on","task":"Hierarchical Multi-label Classification","dataset":"Cellcycle Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.252"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-8","task":"Hierarchical Multi-label Classification","dataset":"Cellcycle GO","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.400"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-1","task":"Hierarchical Multi-label Classification","dataset":"Derisi Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.193"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-9","task":"Hierarchical Multi-label Classification","dataset":"Derisi GO","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.369"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-2","task":"Hierarchical Multi-label Classification","dataset":"Eisen Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.298"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-10","task":"Hierarchical Multi-label Classification","dataset":"Eisen GO","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.440"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-3","task":"Hierarchical Multi-label Classification","dataset":"Expr Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.301"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-11","task":"Hierarchical Multi-label Classification","dataset":"Expr GO","model":"HMCN-F","rank_in_archive_order":1,"of":2,"metrics":{"AU(PRC)":"0.452"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-4","task":"Hierarchical Multi-label Classification","dataset":"Gasch1 Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.284"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-12","task":"Hierarchical Multi-label Classification","dataset":"Gasch1 GO","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.428"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-5","task":"Hierarchical Multi-label Classification","dataset":"Gasch2 Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.254"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-13","task":"Hierarchical Multi-label Classification","dataset":"Gasch2 GO","model":"HMCN-F","rank_in_archive_order":1,"of":2,"metrics":{"AU(PRC)":"0.465"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-6","task":"Hierarchical Multi-label Classification","dataset":"Seq Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.291"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-14","task":"Hierarchical Multi-label Classification","dataset":"Seq GO","model":"HMCN-F","rank_in_archive_order":1,"of":2,"metrics":{"AU(PRC)":"0.447"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-7","task":"Hierarchical Multi-label Classification","dataset":"Spo Funcat","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.211"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-15","task":"Hierarchical Multi-label Classification","dataset":"Spo GO","model":"HMCN-F","rank_in_archive_order":2,"of":2,"metrics":{"AU(PRC)":"0.376"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"936b5d57522424b33a0da2e68c66980576eeb4ff306ca4f28487f8f3ddac2425","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}