乐胖代购免代理版

{"id":"https://openalex.org/W4387559923","doi":"https://doi.org/10.48550/arxiv.2310.05331","title":"Unlearning with Fisher Masking","display_name":"Unlearning with Fisher Masking","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387559923","doi":"https://doi.org/10.48550/arxiv.2310.05331"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.05331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2310.05331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100761346","display_name":"Yufang Liu","orcid":"https://orcid.org/0009-0006-8949-0617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yufang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100890759","display_name":"Changzhi Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Changzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040048158","display_name":"WU Yuan-bin","orcid":"https://orcid.org/0009-0005-1562-9121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yuanbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050248676","display_name":"Aimin Zhou","orcid":"https://orcid.org/0000-0002-4768-5946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Aimin","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":65},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9812,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9812,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9534,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9435,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.93173015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142796},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4908951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41570127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36269188},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.05331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2310.05331","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.05331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4306674287","https://openalex.org/W4283697347","https://openalex.org/W4210805261","https://openalex.org/W3170094116","https://openalex.org/W3107602296","https://openalex.org/W3046775127","https://openalex.org/W2961085424"],"abstract_inverted_index":{"Machine":[0],"unlearning":[1,59,72,119],"aims":[2],"to":[3,12,71,117],"revoke":[4],"some":[5,51],"training":[6],"data":[7,32],"after":[8],"learning":[9],"in":[10],"response":[11],"requests":[13],"from":[14],"users,":[15],"model":[16],"developers,":[17],"and":[18,81],"administrators.":[19],"Most":[20],"previous":[21],"methods":[22],"are":[23],"based":[24,73],"on":[25,38,74,78,107],"direct":[26],"fine-tuning,":[27,55,92],"which":[28],"may":[29],"neither":[30],"remove":[31],"completely":[33,100],"nor":[34],"retain":[35],"full":[36],"performances":[37,57],"the":[39,56,85,88,93,105,108],"remain":[40,109],"data.":[41,110],"In":[42],"this":[43],"work,":[44],"we":[45],"find":[46],"that,":[47],"by":[48],"first":[49],"masking":[50,68,96],"important":[52],"parameters":[53],"before":[54],"of":[58,87,104],"could":[60,97],"be":[61],"significantly":[62],"improved.":[63],"We":[64],"propose":[65],"a":[66],"new":[67],"strategy":[69],"tailored":[70],"Fisher":[75,95],"information.":[76],"Experiments":[77],"various":[79],"datasets":[80],"network":[82],"structures":[83],"show":[84],"effectiveness":[86],"method:":[89],"without":[90],"any":[91],"proposed":[94],"unlearn":[98],"almost":[99],"while":[101],"maintaining":[102],"most":[103],"performance":[106],"It":[111],"also":[112],"exhibits":[113],"stronger":[114],"stability":[115],"compared":[116],"other":[118],"baselines":[120]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4387559923","counts_by_year":[],"updated_date":"2025-04-08T23:01:32.817265","created_date":"2023-10-12"}