{"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/negmerge-consensual-weight-negation-for","title":"NegMerge: Consensual Weight Negation for Strong Machine Unlearning","arxiv_id":"2410.05583","date":"2024-10-08","proceeding":null,"authors":["Hyoseo Kim","Dongyoon Han","Junsuk Choe"],"abstract":"Machine unlearning aims to selectively remove specific knowledge from a model. Current methods, such as task arithmetic, rely on fine-tuning models on the forget set, generating a task vector, and subtracting it from the original model. However, we argue the effectiveness of this approach is highly sensitive to hyperparameter selection, necessitating careful validation to identify the best model among many fine-tuned candidates. In this paper, we propose a novel method that leverages all given fine-tuned models rather than selecting a single one. By constructing task vectors from models trained with varied hyperparameters and merging only the components of the task vectors with consistent signs, we perform unlearning by negating the merged task vector from the original model. Given that existing methods also utilize multiple fine-tuned models, our approach delivers more effective unlearning without incurring additional computational costs. We demonstrate the effectiveness of our method on both vision-language models and standard image classification models, showing improved unlearning performance with minimal degradation on the retain set, outperforming state-of-the-art techniques.","url_abs":"https://arxiv.org/abs/2410.05583v1","url_pdf":"https://arxiv.org/pdf/2410.05583v1.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":"negmerge-consensual-weight-negation-for","repo_url":"https://github.com/naver-ai/negmerge","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"},{"task_slug":"negation","task_name":"Negation"},{"task_slug":"task-arithmetic","task_name":"Task Arithmetic"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.05583","atlas_url":"https://app.syntology.ai/?focus=2410.05583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05583"}},"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":"deterministic:regex_extraction","url":"https://github.com/naver-ai/negmerge","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"2d5d7a12d8de02b7","entry":"cosine_lr","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/utils.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"code_sha256_prefix":"7d9de96609777711","entry":"custom_scaled_dot_product_attention","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/modeling.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7d9de96609777711"}},{"code_sha256_prefix":"23886ccd64a06f48","entry":"get_module_by_name","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/modeling.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"23886ccd64a06f48"}},{"code_sha256_prefix":"aafcff3ad1ccef6e","entry":"accuracy","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/utils.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aafcff3ad1ccef6e"}},{"code_sha256_prefix":"57acc0bee3da475a","entry":"distribute_loader","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/distributed.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/distributed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"57acc0bee3da475a"}},{"code_sha256_prefix":"7d051a7adefedb6c","entry":"torch_load_old","repo":"naver-ai/negmerge","repo_kind":"official","path":"CLIP_MU/src/utils.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d051a7adefedb6c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}