{"id":"https://openalex.org/W7124943637","doi":"https://doi.org/10.1109/cbmi66578.2025.11339308","title":"Towards Graph-Based Federated Learning: ModelNet - A ResNet-based Model Classification Dataset","display_name":"Towards Graph-Based Federated Learning: ModelNet - A ResNet-based Model Classification Dataset","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124943637","doi":"https://doi.org/10.1109/cbmi66578.2025.11339308"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123434882","display_name":"Abhisek Ray","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Abhisek Ray","raw_affiliation_strings":["Aarhus University,Electrical and Computer Engineering,Aarhus,Denmark"],"raw_orcid":"https://orcid.org/0000-0002-0551-5674","affiliations":[{"raw_affiliation_string":"Aarhus University,Electrical and Computer Engineering,Aarhus,Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123253081","display_name":"Lukas Esterle","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lukas Esterle","raw_affiliation_strings":["Aarhus University,Electrical and Computer Engineering,Aarhus,Denmark"],"raw_orcid":"https://orcid.org/0000-0002-0248-1552","affiliations":[{"raw_affiliation_string":"Aarhus University,Electrical and Computer Engineering,Aarhus,Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123434882"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82349938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9391999840736389,"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":0.9391999840736389,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.01730000041425228,"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":0.007499999832361937,"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":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7218000292778015},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6608999967575073},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5938000082969666},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.40059998631477356},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3962000012397766},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077999949455261},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7218000292778015},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5162000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3091635927","https://openalex.org/W3193589553","https://openalex.org/W4399479147","https://openalex.org/W4404915958"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"has":[3,34],"emerged":[4],"as":[5],"a":[6,30,36,60,72,83,133,154,222,250],"powerful":[7],"paradigm":[8],"for":[9,63,183,253],"training":[10],"machine":[11],"learning":[12],"models":[13],"across":[14],"distributed":[15],"data":[16,20,27,173,207],"sources":[17],"while":[18],"preserving":[19],"locality.":[21],"However,":[22],"the":[23,44,48,57,79,90,117,138,144,150,181,211,218,229,242,245],"privacy":[24,152],"of":[25,38,50,112,213,244],"local":[26,151],"is":[28,163],"always":[29],"pivotal":[31],"concern":[32],"and":[33,53,104,175,186,197,205,238,255,261],"received":[35],"lot":[37],"attention":[39],"in":[40,56,153,180],"recent":[41],"research":[42],"on":[43,116,202,235],"FL":[45,139,168,189,225,257],"regime.":[46],"Moreover,":[47],"lack":[49],"domain":[51,100,236],"heterogeneity":[52],"client-specific":[54,96,110,224],"segregation":[55],"benchmarks":[58],"remains":[59],"critical":[61],"bottleneck":[62],"rigorous":[64],"evaluation.":[65],"In":[66,125],"this":[67],"paper,":[68],"we":[69,88,107,131,216],"introduce":[70],"ModelNet,":[71],"novel":[73],"image":[74,129],"classification":[75],"dataset":[76,93,226,260],"constructed":[77],"from":[78,82],"embeddings":[80],"extracted":[81],"pre-trained":[84,118],"ResNet50":[85,119],"model.":[86],"First,":[87],"modify":[89],"CI-F":[91],"AR100":[92],"into":[94],"three":[95,99,114,192],"variants,":[97,247],"considering":[98],"heterogeneities":[101],"(homogeneous,":[102],"heterogeneous,":[103,204],"random).":[105],"Subsequently,":[106],"train":[108],"each":[109],"subset":[111],"all":[113],"variants":[115,193],"model":[120,123,146],"to":[121,127,136,148,159,165,220],"save":[122],"parameters.":[124],"addition":[126],"multi-domain":[128],"data,":[130],"propose":[132,221],"new":[134],"hypothesis":[135],"define":[137],"algorithm":[140],"that":[141],"can":[142],"access":[143],"anonymized":[145],"parameters":[147],"preserve":[149],"more":[155],"effective":[156],"manner":[157],"compared":[158],"existing":[160],"ones.":[161],"ModelNet":[162],"designed":[164],"simulate":[166],"realistic":[167],"settings":[169],"by":[170],"incorporating":[171],"non-IID":[172],"distributions":[174],"client":[176],"diversity":[177],"design":[178],"principles":[179],"mainframe":[182],"both":[184],"conventional":[185],"futuristic":[187],"graph-driven":[188],"algorithms.":[190],"The":[191,259],"are":[194,200,217,264],"ModelNet-S,":[195],"ModelNet-D,":[196],"ModelNet-R,":[198],"which":[199],"based":[201,234],"homogeneous,":[203],"random":[206],"settings,":[208],"respectively.":[209],"To":[210],"best":[212],"our":[214],"knowledge,":[215],"first":[219],"cross-environment":[223],"along":[227],"with":[228],"graph-based":[230,256],"variant.":[231],"Extensive":[232],"experiments":[233],"shifts":[237],"aggregation":[239],"strategies":[240],"show":[241],"effectiveness":[243],"above":[246],"making":[248],"it":[249],"practical":[251],"benchmark":[252],"classical":[254],"research.":[258],"related":[262],"code":[263],"available":[265],"here11https://github.com/rayabhisek123/ModelNet":[266]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}