{"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/zlpr-a-novel-loss-for-multi-label","title":"ZLPR: A Novel Loss for Multi-label Classification","arxiv_id":"2208.02955","date":"2022-08-05","proceeding":null,"authors":["Jianlin Su","Mingren Zhu","Ahmed Murtadha","Shengfeng Pan","Bo Wen","Yunfeng Liu"],"abstract":"In the era of deep learning, loss functions determine the range of tasks available to models and algorithms. To support the application of deep learning in multi-label classification (MLC) tasks, we propose the ZLPR (zero-bounded log-sum-exp \\& pairwise rank-based) loss in this paper. Compared to other rank-based losses for MLC, ZLPR can handel problems that the number of target labels is uncertain, which, in this point of view, makes it equally capable with the other two strategies often used in MLC, namely the binary relevance (BR) and the label powerset (LP). Additionally, ZLPR takes the corelation between labels into consideration, which makes it more comprehensive than the BR methods. In terms of computational complexity, ZLPR can compete with the BR methods because its prediction is also label-independent, which makes it take less time and memory than the LP methods. Our experiments demonstrate the effectiveness of ZLPR on multiple benchmark datasets and multiple evaluation metrics. Moreover, we propose the soft version and the corresponding KL-divergency calculation method of ZLPR, which makes it possible to apply some regularization tricks such as label smoothing to enhance the generalization of models.","url_abs":"https://arxiv.org/abs/2208.02955v1","url_pdf":"https://arxiv.org/pdf/2208.02955v1.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":"zlpr-a-novel-loss-for-multi-label","repo_url":"https://github.com/whitepurple/HBM-loss-for-HTC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"zlpr-loss","method_name":"ZLPR Loss"}],"datasets_introduced":[],"methods_introduced":[{"slug":"zlpr-loss","name":"ZLPR Loss","full_name":"Zero-bounded Log-sum-exp & Pairwise Rank-based Loss"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.02955","atlas_url":"https://app.syntology.ai/?focus=2208.02955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02955"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whitepurple/HBM-loss-for-HTC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":"382f2c9402b853d4","entry":"cleaning","repo":"whitepurple/HBM-loss-for-HTC","repo_kind":"listed","path":"src/preprocess/eurlex57k_preprocessor.py","file_url":"https://github.com/whitepurple/HBM-loss-for-HTC/blob/HEAD/src/preprocess/eurlex57k_preprocessor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"382f2c9402b853d4"}},{"code_sha256_prefix":"d995c92577dc8eb1","entry":"get_criterion","repo":"whitepurple/HBM-loss-for-HTC","repo_kind":"listed","path":"src/utils/criterion.py","file_url":"https://github.com/whitepurple/HBM-loss-for-HTC/blob/HEAD/src/utils/criterion.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d995c92577dc8eb1"}},{"code_sha256_prefix":"d8ec073697b5fb3d","entry":"get_decoder","repo":"whitepurple/HBM-loss-for-HTC","repo_kind":"listed","path":"src/model/decoder.py","file_url":"https://github.com/whitepurple/HBM-loss-for-HTC/blob/HEAD/src/model/decoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8ec073697b5fb3d"}},{"code_sha256_prefix":"fb0ffb0816f127ab","entry":"list_chunk","repo":"whitepurple/HBM-loss-for-HTC","repo_kind":"listed","path":"src/dataset/caching.py","file_url":"https://github.com/whitepurple/HBM-loss-for-HTC/blob/HEAD/src/dataset/caching.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb0ffb0816f127ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}