{"id":"https://openalex.org/W4410118246","doi":"https://doi.org/10.1109/tnnls.2025.3562164","title":"FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification","display_name":"FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification","publication_year":2025,"publication_date":"2025-05-06","ids":{"openalex":"https://openalex.org/W4410118246","doi":"https://doi.org/10.1109/tnnls.2025.3562164","pmid":"https://pubmed.ncbi.nlm.nih.gov/40327480"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3562164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3562164","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5133952064","display_name":"Hui CHEN","orcid":"https://orcid.org/0000-0003-1375-4664"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1375-4664","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102633178","display_name":"Hengyu Liu","orcid":"https://orcid.org/0009-0007-7965-1402"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Hengyu Liu","raw_affiliation_strings":["Department of Computer Science, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036594859","display_name":"Zhangkai Wu","orcid":"https://orcid.org/0000-0001-5494-0768"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhangkai Wu","raw_affiliation_strings":["Faculty of Engineering and Information Technology,, University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology,, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102795366","display_name":"Xuhui Fan","orcid":"https://orcid.org/0000-0002-7558-7200"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuhui Fan","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7558-7200","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000798681","display_name":"Longbing Cao","orcid":"https://orcid.org/0000-0003-1562-9429"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Longbing Cao","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1562-9429","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.436,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.99535706,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"36","issue":"9","first_page":"16975","last_page":"16989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.79830002784729,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.79830002784729,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.7821999788284302,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7211999893188477,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/subnetwork","display_name":"Subnetwork","score":0.9117485284805298},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7454086542129517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641325950622559},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32930219173431396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3274267315864563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3258700966835022},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10603177547454834}],"concepts":[{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.9117485284805298},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7454086542129517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641325950622559},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32930219173431396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3274267315864563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3258700966835022},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10603177547454834}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2025.3562164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3562164","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40327480","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40327480","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:pure.atira.dk:publications/752a1d02-3fb5-400f-bf39-86041d1e9cac","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/752a1d02-3fb5-400f-bf39-86041d1e9cac","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, H, Liu, H, Wu, Z, Fan, X & Cao, L 2025, 'FedSI : Federated Subnetwork Inference for Efficient Uncertainty Quantification', IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 9, pp. 16975-16989. https://doi.org/10.1109/TNNLS.2025.3562164","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1524969253","display_name":"Data Complexity and Uncertainty-Resilient Deep Variational Learning","funder_award_id":"DP240102050","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G2177096475","display_name":"Deep Interaction Learning in Unlabelled Big Data and Complex Systems","funder_award_id":"FT190100734","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G3916023789","display_name":"Ethical Enterprise Representations for Personalised Sustainable Finance","funder_award_id":"LP230201022","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G5589738817","display_name":"Federated Omniverse Facilities for Smart Digital Futures","funder_award_id":"LE240100131","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G716332117","display_name":"Deep analytics of non-occurring but important behaviours","funder_award_id":"DP190101079","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2783538964","https://openalex.org/W2919115771","https://openalex.org/W2995022099","https://openalex.org/W3013931120","https://openalex.org/W3133814152","https://openalex.org/W3149954208","https://openalex.org/W3210034512","https://openalex.org/W4206878041","https://openalex.org/W4212863985","https://openalex.org/W4221049545","https://openalex.org/W4245577611","https://openalex.org/W4286542654","https://openalex.org/W4287851275","https://openalex.org/W4289534001","https://openalex.org/W4290945198","https://openalex.org/W4296425714","https://openalex.org/W4304480072","https://openalex.org/W4318823481","https://openalex.org/W4323644302","https://openalex.org/W4377713808","https://openalex.org/W4385267391","https://openalex.org/W4385875921","https://openalex.org/W4389776620","https://openalex.org/W4390939996","https://openalex.org/W4391102852","https://openalex.org/W4412434916"],"related_works":["https://openalex.org/W2060724872","https://openalex.org/W2082094785","https://openalex.org/W2202198356","https://openalex.org/W3087203342","https://openalex.org/W2377184161","https://openalex.org/W228984114","https://openalex.org/W4226360758","https://openalex.org/W2151093953","https://openalex.org/W2090026684","https://openalex.org/W2907567977"],"abstract_inverted_index":{"While":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)-based":[4],"personalized":[5],"federated":[6,22],"learning":[7,23],"(PFL)":[8],"is":[9,35,65],"demanding":[10],"for":[11,21],"addressing":[12],"data":[13],"heterogeneity":[14],"and":[15,46,67,96,106,131],"shows":[16],"promising":[17],"performance,":[18],"existing":[19,129],"methods":[20,72],"(FL)":[24],"suffer":[25],"from":[26],"efficient":[27],"systematic":[28,75,112],"uncertainty":[29],"quantification.":[30],"The":[31],"Bayesian":[32,57,71,130],"DNNs-based":[33,58],"PFL":[34,62],"usually":[36],"questioned":[37],"of":[38],"either":[39],"oversimplified":[40],"model":[41],"structures":[42],"or":[43],"high":[44],"computational":[45],"memory":[47],"costs.":[48],"In":[49],"this":[50],"article,":[51],"we":[52],"introduce":[53],"FedSI,":[54],"a":[55,80],"novel":[56],"subnetwork":[59],"inference":[60,108],"(SI)":[61],"framework.":[63],"FedSI":[64,103,127],"simple":[66],"scalable":[68,107],"by":[69],"leveraging":[70],"to":[73,90,114],"incorporate":[74],"uncertainties":[76,113],"effectively.":[77],"It":[78],"implements":[79],"client-specific":[81],"SI":[82],"mechanism,":[83],"selects":[84],"network":[85],"parameters":[86],"with":[87],"large":[88],"variance":[89],"be":[91],"inferred":[92],"through":[93],"posterior":[94],"distributions,":[95],"fixes":[97],"the":[98,111,115],"rest":[99],"as":[100],"deterministic":[101],"ones.":[102],"achieves":[104],"fast":[105],"while":[109],"preserving":[110],"fullest":[116],"extent.":[117],"Extensive":[118],"experiments":[119],"on":[120],"four":[121],"different":[122],"benchmark":[123],"datasets":[124],"demonstrate":[125],"that":[126],"outperforms":[128],"non-Bayesian":[132],"FL":[133,137],"baselines":[134],"in":[135],"heterogeneous":[136],"scenarios.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":18}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}