{"id":"https://openalex.org/W7158859680","doi":"https://doi.org/10.48550/arxiv.2604.26467","title":"Differentially Private Contrastive Learning via Bounding Group-level Contribution","display_name":"Differentially Private Contrastive Learning via Bounding Group-level Contribution","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158859680","doi":"https://doi.org/10.48550/arxiv.2604.26467"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26467","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_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.26467","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023099893","display_name":"Kecen Li","orcid":"https://orcid.org/0009-0004-2266-8113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kecen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134919018","display_name":"Chen Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134909528","display_name":"Zinan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134910215","display_name":"Tianhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tianhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010903591","display_name":"Xiaokui Xiao","orcid":"https://orcid.org/0000-0003-0914-4580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Xiaokui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"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":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.82669997215271,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.82669997215271,"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":0.052400000393390656,"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/T11448","display_name":"Face recognition and analysis","score":0.025800000876188278,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7932000160217285},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5814999938011169},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.4104999899864197},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3614000082015991},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3495999872684479},{"id":"https://openalex.org/keywords/private-information-retrieval","display_name":"Private information retrieval","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7932000160217285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837000250816345},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720999836921692},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C108801101","wikidata":"https://www.wikidata.org/wiki/Q15032","display_name":"Steganography","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26467","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_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.26467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26467","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_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.42471224069595337,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Differentially":[0],"private":[1,27],"(DP)":[2],"contrastive":[3,47,75,93,171,193],"learning":[4,76,94,172],"aims":[5],"to":[6,39,118],"learn":[7],"general-purpose":[8],"representations":[9],"from":[10,34],"sensitive":[11],"data,":[12],"alleviating":[13],"the":[14,40,59,62,130,161,164],"privacy":[15,149,175],"leakage":[16],"concerns":[17],"of":[18,64,133,163],"organizations":[19],"deploying":[20],"or":[21],"sharing":[22],"embedding":[23],"models":[24],"trained":[25],"on":[26,54],"user":[28],"content.":[29],"However,":[30],"existing":[31,191],"approaches":[32],"suffer":[33],"severe":[35],"utility":[36],"degradation":[37],"due":[38],"over-strong":[41],"inter-sample":[42,82],"dependency":[43,100],"inherent":[44],"in":[45,58,166],"standard":[46],"objectives,":[48],"where":[49],"each":[50,107],"sample's":[51],"gradient":[52,99,123],"depends":[53],"all":[55],"other":[56],"samples":[57,117],"batch,":[60],"amplifying":[61],"impact":[63],"DP":[65,74,92,192],"noise.":[66],"In":[67],"this":[68,85],"work,":[69],"we":[70,87,137],"argue":[71],"that":[72,96,157],"effective":[73],"requires":[77],"explicitly":[78],"reducing":[79,126],"such":[80],"intrinsic":[81],"reliance.":[83],"To":[84,128],"end,":[86],"propose":[88],"DP-GCL,":[89],"a":[90],"principled":[91],"framework":[95],"structurally":[97],"limits":[98],"through":[101],"bounding":[102],"group-level":[103],"contribution.":[104],"DP-GCL":[105,158],"partitions":[106],"batch":[108],"into":[109],"small,":[110],"disjoint":[111],"groups":[112],"and":[113,125,169,184],"restricts":[114],"available":[115],"negative":[116,134,145],"within-group":[119],"samples,":[120],"thereby":[121],"localizing":[122],"influence":[124],"sensitivity.":[127],"counteract":[129],"resulting":[131],"loss":[132],"sample":[135],"diversity,":[136],"further":[138],"introduce":[139],"intra-group":[140],"augmentation,":[141],"which":[142],"generates":[143],"additional":[144],"views":[146],"without":[147],"increasing":[148],"cost.":[150],"Extensive":[151],"experiments":[152],"across":[153],"eight":[154],"datasets":[155],"demonstrate":[156],"consistently":[159],"advances":[160],"state":[162],"art":[165],"both":[167],"uni-modal":[168],"multi-modal":[170],"under":[173],"practical":[174],"budgets:":[176],"it":[177],"improves":[178],"image":[179],"classification":[180],"accuracy":[181,187],"by":[182,188],"5.6%":[183],"image-text":[185],"retrieval":[186],"20.1%":[189],"over":[190],"methods.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-01T00:00:00"}