{"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/hill-hierarchy-aware-information-lossless","title":"HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification","arxiv_id":"2403.17307","date":"2024-03-26","proceeding":null,"authors":["He Zhu","Junran Wu","Ruomei Liu","Yue Hou","Ze Yuan","Shangzhe Li","YiCheng Pan","Ke Xu"],"abstract":"Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information. In this paper, we tend to investigate the feasibility of a contrastive learning scheme in which the semantic and syntactic information inherent in the input sample is adequately reserved in the contrastive samples and fused during the learning process. Specifically, we propose an information lossless contrastive learning strategy for HTC, namely \\textbf{H}ierarchy-aware \\textbf{I}nformation \\textbf{L}ossless contrastive \\textbf{L}earning (HILL), which consists of a text encoder representing the input document, and a structure encoder directly generating the positive sample. The structure encoder takes the document embedding as input, extracts the essential syntactic information inherent in the label hierarchy with the principle of structural entropy minimization, and injects the syntactic information into the text representation via hierarchical representation learning. Experiments on three common datasets are conducted to verify the superiority of HILL.","url_abs":"https://arxiv.org/abs/2403.17307v1","url_pdf":"https://arxiv.org/pdf/2403.17307v1.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":"hill-hierarchy-aware-information-lossless","repo_url":"https://github.com/rooooyy/hill","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"document-embedding","task_name":"Document Embedding"},{"task_slug":"hierarchical-multi-label-classification","task_name":"Hierarchical Multi-label Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"htc","method_name":"HTC"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hierarchical-multi-label-classification-on-18","task":"Hierarchical Multi-label Classification","dataset":"New York Times Annotated Corpus","model":"HILL","rank_in_archive_order":3,"of":7,"metrics":{"Macro F1":"69.96","Micro F1":"80.47"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-17","task":"Hierarchical Multi-label Classification","dataset":"RCV1-v2","model":"HILL","rank_in_archive_order":5,"of":7,"metrics":{"Macro F1":"70.12","Micro F1":"87.31"},"uses_additional_data":false},{"leaderboard":"/sota/hierarchical-multi-label-classification-on-16","task":"Hierarchical Multi-label Classification","dataset":"WOS","model":"HILL","rank_in_archive_order":1,"of":3,"metrics":{"Macro F1":"81.77","Micro F1":"87.28"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.17307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17307"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Rooooyy/HILL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b16d0d091d08f27f","entry":"child_tree_deepth","repo":"Rooooyy/HILL","repo_kind":"official","path":"model/coding_tree.py","file_url":"https://github.com/Rooooyy/HILL/blob/HEAD/model/coding_tree.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b16d0d091d08f27f"}},{"code_sha256_prefix":"721b31dc7e862365","entry":"cut_volume","repo":"Rooooyy/HILL","repo_kind":"official","path":"model/coding_tree.py","file_url":"https://github.com/Rooooyy/HILL/blob/HEAD/model/coding_tree.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"721b31dc7e862365"}},{"code_sha256_prefix":"21dda7ecf92b5b2c","entry":"graph_parse","repo":"Rooooyy/HILL","repo_kind":"official","path":"model/coding_tree.py","file_url":"https://github.com/Rooooyy/HILL/blob/HEAD/model/coding_tree.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21dda7ecf92b5b2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}