{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/joint-learning-of-hyperbolic-label-embeddings","title":"Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification","arxiv_id":"2101.04997","date":"2021-01-13","proceeding":"EACL 2021 2","authors":["Soumya Chatterjee","Ayush Maheshwari","Ganesh Ramakrishnan","Saketha Nath Jagaralpudi"],"abstract":"We consider the problem of multi-label classification where the labels lie in a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the recent success of hyperbolic embeddings in capturing hierarchical relations, we propose to jointly learn the classifier parameters as well as the label embeddings. Such a joint learning is expected to provide a twofold advantage: i) the classifier generalizes better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy. We propose a novel formulation for the joint learning and empirically evaluate its efficacy. The results show that the joint learning improves over the baseline that employs label co-occurrence based pre-trained hyperbolic embeddings. Moreover, the proposed classifiers achieve state-of-the-art generalization on standard benchmarks. We also present evaluation of the hyperbolic embeddings obtained by joint learning and show that they represent the hierarchy more accurately than the other alternatives.","url_abs":"https://arxiv.org/abs/2101.04997v1","url_pdf":"https://arxiv.org/pdf/2101.04997v1.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":[{"paper_slug":"joint-learning-of-hyperbolic-label-embeddings","repo_url":"https://github.com/soumyac1999/hyperbolic-label-emb-for-hmc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"multi-label-text-classification","task_name":"Multi-Label Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-text-classification-on-rcv1","task":"Multi-Label Text Classification","dataset":"RCV1","model":"HiddeN","rank_in_archive_order":1,"of":1,"metrics":{"Macro-F1":"47.3","Micro-F1":"79.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.04997","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}