{"id":"https://openalex.org/W7139961356","doi":"https://doi.org/10.48550/arxiv.2603.18540","title":"GAPSL: A Gradient-Aligned Parallel Split Learning on Heterogeneous Data","display_name":"GAPSL: A Gradient-Aligned Parallel Split Learning on Heterogeneous Data","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139961356","doi":"https://doi.org/10.48550/arxiv.2603.18540"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18540","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130220713","display_name":"Zheng Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066189735","display_name":"Ons Aouedi","orcid":"https://orcid.org/0000-0002-2343-0850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aouedi, Ons","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130221615","display_name":"Wei Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130219597","display_name":"Symeon Chatzinotas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chatzinotas, Symeon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130245670","display_name":"Xianhao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xianhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5130220713"],"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2549999952316284,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2549999952316284,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2054000049829483,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.10580000281333923,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/construct","display_name":"Construct (python library)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.482699990272522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.450300008058548},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4302999973297119},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42309999465942383},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.350600004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641000151634216},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4302999973297119},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18540","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18540","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":"article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4539942443370819}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"of":[3,100],"neural":[4],"networks":[5],"poses":[6],"significant":[7],"challenges":[8],"for":[9,47],"democratizing":[10],"FL":[11],"on":[12,143],"resource?constrained":[13],"client":[14,103],"devices.":[15],"Parallel":[16],"split":[17],"learning":[18],"(PSL)":[19],"has":[20],"emerged":[21],"as":[22],"a":[23,32,77,98,107,118,144],"promising":[24],"solution":[25],"by":[26],"offloading":[27],"substantial":[28],"computing":[29,39,146],"workload":[30],"to":[31,105,121],"server":[33],"via":[34],"model":[35,45,138],"partitioning,":[36],"shrinking":[37],"client-side":[38,44],"load,":[40],"and":[41,50,90,136,160],"eliminating":[42],"the":[43,112,127],"aggregation":[46],"reduced":[48],"communication":[49],"deployment":[51],"costs.":[52],"Since":[53],"PSL":[54,79],"is":[55],"aggregation-free,":[56],"it":[57],"suffers":[58],"from":[59,64],"severe":[60],"training":[61,158],"divergence":[62],"stemming":[63],"gradient":[65,87,91,109,125,133],"directional":[66,134],"inconsistency":[67,135],"across":[68],"clients.":[69],"To":[70],"address":[71],"this":[72],"challenge,":[73],"we":[74],"propose":[75],"GAPSL,":[76],"gradient-aligned":[78],"framework":[80],"that":[81,110,151],"comprises":[82],"two":[83],"key":[84],"components:":[85],"leader":[86,108,128],"identification":[88],"(LGI)":[89],"direction":[92],"alignment":[93],"(GDA).":[94],"LGI":[95],"dynamically":[96],"selects":[97],"set":[99],"directionally":[101],"consistent":[102],"gradients":[104],"construct":[106],"captures":[111],"global":[113],"convergence":[114],"trend.":[115],"GDA":[116],"employs":[117],"direction-aware":[119],"regularization":[120],"align":[122],"each":[123],"client's":[124],"with":[126],"gradient,":[129],"thereby":[130],"mitigating":[131],"inter-device":[132],"enhancing":[137],"convergence.":[139],"We":[140],"evaluate":[141],"GAPSL":[142,152],"prototype":[145],"testbed.":[147],"Extensive":[148],"experiments":[149],"demonstrate":[150],"consistently":[153],"outperforms":[154],"state-of-the-art":[155],"benchmarks":[156],"in":[157],"accuracy":[159],"latency.":[161]},"counts_by_year":[],"updated_date":"2026-03-21T06:36:02.116451","created_date":"2026-03-21T00:00:00"}