{"id":"https://openalex.org/W7171995784","doi":"https://doi.org/10.1145/3774521.3774580","title":"Personalized Federated Autoencoders: Unsupervised Representation Learning at the Edge","display_name":"Personalized Federated Autoencoders: Unsupervised Representation Learning at the Edge","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171995784","doi":"https://doi.org/10.1145/3774521.3774580"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774580","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774580","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144104818","display_name":"Kanika Arora","orcid":"https://orcid.org/0000-0002-2429-1194"},"institutions":[{"id":"https://openalex.org/I1301653859","display_name":"nLIGHT (United States)","ror":"https://ror.org/01se7j361","country_code":"US","type":"company","lineage":["https://openalex.org/I1301653859"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanika Arora","raw_affiliation_strings":["LightMetrics Technologies Pvt. Ltd., Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-2429-1194","affiliations":[{"raw_affiliation_string":"LightMetrics Technologies Pvt. Ltd., Bengaluru, India","institution_ids":["https://openalex.org/I1301653859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034936690","display_name":"Nazreen Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nazreen Shah","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-5059-8739","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144161707","display_name":"Ashish Sethi","orcid":"https://orcid.org/0000-0001-8253-6586"},"institutions":[{"id":"https://openalex.org/I1301653859","display_name":"nLIGHT (United States)","ror":"https://ror.org/01se7j361","country_code":"US","type":"company","lineage":["https://openalex.org/I1301653859"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Sethi","raw_affiliation_strings":["LightMetrics Technologies Pvt. Ltd., Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0001-8253-6586","affiliations":[{"raw_affiliation_string":"LightMetrics Technologies Pvt. Ltd., Bengaluru, India","institution_ids":["https://openalex.org/I1301653859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064173467","display_name":"Ranjitha Prasad","orcid":"https://orcid.org/0000-0002-2649-7882"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ranjitha Prasad","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-2649-7882","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080328045","display_name":"Mithun Uliyar","orcid":null},"institutions":[{"id":"https://openalex.org/I1301653859","display_name":"nLIGHT (United States)","ror":"https://ror.org/01se7j361","country_code":"US","type":"company","lineage":["https://openalex.org/I1301653859"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mithun Uliyar","raw_affiliation_strings":["LightMetrics Technologies Pvt. Ltd., Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-8537-1649","affiliations":[{"raw_affiliation_string":"LightMetrics Technologies Pvt. Ltd., Bengaluru, India","institution_ids":["https://openalex.org/I1301653859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144145188","display_name":"Krishna A G","orcid":"https://orcid.org/0000-0002-5770-8953"},"institutions":[{"id":"https://openalex.org/I1301653859","display_name":"nLIGHT (United States)","ror":"https://ror.org/01se7j361","country_code":"US","type":"company","lineage":["https://openalex.org/I1301653859"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna A G","raw_affiliation_strings":["LightMetrics Technologies Pvt. Ltd., Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-5770-8953","affiliations":[{"raw_affiliation_string":"LightMetrics Technologies Pvt. Ltd., Bengaluru, India","institution_ids":["https://openalex.org/I1301653859"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7468000054359436},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6743000149726868},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5489000082015991},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5074999928474426},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4952999949455261},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.48730000853538513},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47279998660087585},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4616999924182892},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4032000005245209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086000084877014},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7468000054359436},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230999827384949},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5964000225067139},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5074999928474426},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774580","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774580","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2100495367","https://openalex.org/W2102605133","https://openalex.org/W2163922914","https://openalex.org/W2767028605","https://openalex.org/W2781091734","https://openalex.org/W2882997960","https://openalex.org/W2898186212","https://openalex.org/W2951635356","https://openalex.org/W2995022099","https://openalex.org/W3018102029","https://openalex.org/W3026182744","https://openalex.org/W3034715187","https://openalex.org/W3086755561","https://openalex.org/W3089578458","https://openalex.org/W3171007011","https://openalex.org/W3186051974","https://openalex.org/W3193756050","https://openalex.org/W3204715535","https://openalex.org/W4283367167","https://openalex.org/W4312592506","https://openalex.org/W7133192773"],"related_works":[],"abstract_inverted_index":{"Modern-day":[0],"applications":[1],"such":[2],"as":[3,92],"autonomous":[4],"vehicles,":[5],"IoT,":[6],"smart":[7],"grids,":[8],"etc.,":[9],"generate":[10],"massive":[11],"amounts":[12],"of":[13,59,75,117,200,207,216,225],"data":[14,26,48,80],"at":[15,49,107],"the":[16,50,57,72,108,114,118,130,138,147,159,214,226,231],"edge.":[17],"Federated":[18,95],"Learning":[19],"(FL)":[20],"enables":[21],"machine":[22],"learning":[23,44,67,180],"without":[24],"requiring":[25],"to":[27,33,56,91,185,197,203,211],"be":[28],"transferred":[29],"from":[30],"edge":[31,51],"devices":[32],"any":[34],"untrusted":[35],"third":[36],"party.":[37],"A":[38],"fundamental":[39],"challenge":[40],"in":[41,81,142,151,213],"federated":[42,66],"supervised":[43],"is":[45,52,140,195],"ensuring":[46],"that":[47,168],"annotated.":[53],"Furthermore,":[54],"due":[55],"curse":[58],"statistical":[60],"heterogeneity":[61],"across":[62],"clients,":[63,208],"adopting":[64],"personalized":[65,83],"has":[68],"become":[69],"essential":[70],"for":[71,98],"successful":[73],"deployment":[74],"FL.":[76],"To":[77],"utilize":[78],"unlabeled":[79],"a":[82,87,121,133,152,162,204,222],"manner,":[84,154],"we":[85,112],"propose":[86],"novel":[88],"framework,":[89],"referred":[90],"Personalized":[93],"Unsupervised":[94],"AutoEncoders":[96],"(pFedAE),":[97],"obtaining":[99],"globally":[100],"rich":[101],"and":[102,123,155,178,209,234,239],"locally":[103],"relevant":[104],"feature":[105],"representations":[106],"clients.":[109],"In":[110,189],"particular,":[111,190],"partition":[113],"optimization":[115,126],"framework":[116],"autoencoder":[119],"into":[120],"global":[122],"per-client":[124],"local":[125,217],"problem.":[127],"We":[128,166,219],"evaluate":[129],"representation":[131,139,160],"on":[132],"downstream":[134],"classification":[135],"task,":[136],"where":[137],"assessed":[141],"two":[143],"ways:":[144],"first,":[145],"using":[146,161,230,236],"linear":[148,176],"probe":[149,177],"strategy":[150],"stand-alone":[153],"second,":[156],"by":[157],"fine-tuning":[158],"semi-supervised":[163,179],"evaluation":[164,181],"strategy.":[165],"demonstrate":[167],"pFedAE":[169,191],"achieves":[170],"good":[171],"generalization":[172],"performance":[173],"under":[174],"both":[175],"strategies,":[182],"enabling":[183],"it":[184],"outperform":[186],"state-of-the-art":[187],"baselines.":[188],"demonstrates":[192],"fast":[193],"convergence,":[194],"insensitive":[196],"varying":[198,205],"levels":[199],"heterogeneity,":[201],"scalable":[202],"number":[206,215],"robust":[210],"changes":[212],"epochs.":[218],"also":[220],"provide":[221],"comparative":[223],"assessment":[224],"latent":[227],"space":[228],"obtained":[229],"proposed":[232],"methods":[233],"baselines":[235],"t-SNE":[237],"projections":[238],"angle":[240],"histogram":[241],"plots.":[242]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}