{"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/distribution-level-feature-distancing-for","title":"Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting","arxiv_id":"2409.14747","date":"2024-09-23","proceeding":null,"authors":["Dasol Choi","Dongbin Na"],"abstract":"With the explosive growth of deep learning applications and increasing privacy concerns, the right to be forgotten has become a critical requirement in various AI industries. For example, given a facial recognition system, some individuals may wish to remove their personal data that might have been used in the training phase. Unfortunately, deep neural networks sometimes unexpectedly leak personal identities, making this removal challenging. While recent machine unlearning algorithms aim to enable models to forget specific data, we identify an unintended utility drop-correlation collapse-in which the essential correlations between image features and true labels weaken during the forgetting process. To address this challenge, we propose Distribution-Level Feature Distancing (DLFD), a novel method that efficiently forgets instances while preserving task-relevant feature correlations. Our method synthesizes data samples by optimizing the feature distribution to be distinctly different from that of forget samples, achieving effective results within a single training epoch. Through extensive experiments on facial recognition datasets, we demonstrate that our approach significantly outperforms state-of-the-art machine unlearning methods in both forgetting performance and model utility preservation.","url_abs":"https://arxiv.org/abs/2409.14747v5","url_pdf":"https://arxiv.org/pdf/2409.14747v5.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":"distribution-level-feature-distancing-for","repo_url":"https://github.com/Dasol-Choi/DLFD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.14747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14747"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Dasol-Choi/DLFD","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":"69f8531ba1bb9731","entry":"compute_ot_loss","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"unlearn/dlfd.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/unlearn/dlfd.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69f8531ba1bb9731"}},{"code_sha256_prefix":"4213b87b66625b04","entry":"get_cost_matrix","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"unlearn/dlfd.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/unlearn/dlfd.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4213b87b66625b04"}},{"code_sha256_prefix":"8ce5dd5212668887","entry":"linear_weight_scheduler","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"unlearn/dlfd.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/unlearn/dlfd.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ce5dd5212668887"}},{"code_sha256_prefix":"76ef1f61c3222712","entry":"simple_mia","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"evaluation/mia.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/evaluation/mia.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76ef1f61c3222712"}},{"code_sha256_prefix":"7e66e3d5c261f3c2","entry":"compute_losses","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"evaluation/mia.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/evaluation/mia.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e66e3d5c261f3c2"}},{"code_sha256_prefix":"6d1db600f4359934","entry":"compute_losses_fast","repo":"Dasol-Choi/DLFD","repo_kind":"official","path":"evaluation/mia.py","file_url":"https://github.com/Dasol-Choi/DLFD/blob/HEAD/evaluation/mia.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6d1db600f4359934"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}