{"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/multimodal-machine-unlearning","title":"MultiDelete for Multimodal Machine Unlearning","arxiv_id":"2311.12047","date":"2023-11-18","proceeding":null,"authors":["Jiali Cheng","Hadi Amiri"],"abstract":"Machine Unlearning removes specific knowledge about training data samples from an already trained model. It has significant practical benefits, such as purging private, inaccurate, or outdated information from trained models without the need for complete re-training. Unlearning within a multimodal setting presents unique challenges due to the complex dependencies between different data modalities and the expensive cost of training on large multimodal datasets and architectures. This paper presents the first machine unlearning approach for multimodal data and models, titled MultiDelete, which is designed to decouple associations between unimodal data points during unlearning without losing the overall representation strength of the trained model. MultiDelete advocates for three key properties for effective multimodal unlearning: (a): modality decoupling, which effectively decouples the association between individual unimodal data points marked for deletion, rendering them as unrelated data points, (b): multimodal knowledge retention, which retains the multimodal representation post-unlearning, and (c): unimodal knowledge retention, which retains the unimodal representation postunlearning. MultiDelete is efficient to train and is not constrained by using a strongly convex loss -- a common restriction among existing baselines. Experiments on two architectures and four datasets, including image-text and graph-text datasets, show that MultiDelete gains an average improvement of 17.6 points over best performing baseline in unlearning multimodal samples, can maintain the multimodal and unimodal knowledge of the original model post unlearning, and can provide better protection to unlearned data against adversarial attacks.","url_abs":"https://arxiv.org/abs/2311.12047v2","url_pdf":"https://arxiv.org/pdf/2311.12047v2.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":"multimodal-machine-unlearning","repo_url":"https://github.com/clu-uml/multidelete","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-machine-unlearning","repo_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.12047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12047"}},"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/clu-uml/multidelete","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":2}},"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":7,"samples":[{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"chengjiali/Multimodal-Machine-Unlearning","repo_kind":"official","path":"lavis/models/vit.py","file_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning/blob/HEAD/lavis/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"1993a931a4a905f1","entry":"prepare_dr_data","repo":"clu-uml/multidelete","repo_kind":"official","path":"unlearn.py","file_url":"https://github.com/clu-uml/multidelete/blob/HEAD/unlearn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1993a931a4a905f1"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"chengjiali/Multimodal-Machine-Unlearning","repo_kind":"official","path":"lavis/models/base_model.py","file_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning/blob/HEAD/lavis/models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"chengjiali/Multimodal-Machine-Unlearning","repo_kind":"official","path":"lavis/models/base_model.py","file_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning/blob/HEAD/lavis/models/base_model.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":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"82a78fe29f8d1692","entry":"prepare_df_data","repo":"clu-uml/multidelete","repo_kind":"official","path":"unlearn.py","file_url":"https://github.com/clu-uml/multidelete/blob/HEAD/unlearn.py","link_basis":"first_harvest_node","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":"82a78fe29f8d1692"}},{"code_sha256_prefix":"6a54aa059165fed1","entry":"prepare_df_data","repo":"chengjiali/Multimodal-Machine-Unlearning","repo_kind":"official","path":"get_rep.py","file_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning/blob/HEAD/get_rep.py","link_basis":"first_harvest_node","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":"6a54aa059165fed1"}},{"code_sha256_prefix":"30be9211bacffef7","entry":"prepare_dr_data","repo":"chengjiali/Multimodal-Machine-Unlearning","repo_kind":"official","path":"get_rep.py","file_url":"https://github.com/chengjiali/Multimodal-Machine-Unlearning/blob/HEAD/get_rep.py","link_basis":"first_harvest_node","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":"30be9211bacffef7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}