{"id":"https://openalex.org/W7220996311","doi":"https://doi.org/10.48550/arxiv.2610.09091","title":"FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning","display_name":"FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220996311","doi":"https://doi.org/10.48550/arxiv.2610.09091"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09091","pdf_url":"https://arxiv.org/pdf/2610.09091","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09091","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032997459","display_name":"Konstantinos Ziliaskopoulos","orcid":"https://orcid.org/0000-0001-8323-3392","observed_orcids":["https://orcid.org/0000-0001-8323-3392"]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziliaskopoulos, Konstantinos","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051644960","display_name":"Alexander Vinel","orcid":"https://orcid.org/0000-0003-3095-5986","observed_orcids":["https://orcid.org/0000-0003-3095-5986"]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinel, Alexander","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157909121","display_name":"Jiaqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Jiaqi","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82497590"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9980000257492065,"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":0.9980000257492065,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0010999999940395355,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decision-focused-learning","display_name":"decision-focused learning","score":0.949999988079071},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.9829999804496765},{"id":"https://openalex.org/keywords/cross-silo-federated-learning","display_name":"cross-silo federated learning","score":0.9610000252723694},{"id":"https://openalex.org/keywords/predict-then-optimize","display_name":"predict-then-optimize","score":0.6790000200271606},{"id":"https://openalex.org/keywords/polyhedral-optimization","display_name":"polyhedral optimization","score":0.6420000195503235},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.7850000262260437},{"id":"https://openalex.org/keywords/knapsack-problem","display_name":"knapsack problem","score":0.828000009059906},{"id":"https://openalex.org/keywords/shortest-path","display_name":"shortest path","score":0.8619999885559082},{"id":"https://openalex.org/keywords/energy-pricing","display_name":"energy pricing","score":0.8119999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C32172795","wikidata":"https://www.wikidata.org/wiki/Q4692266","display_name":"Aggregation problem","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09091","pdf_url":"https://arxiv.org/pdf/2610.09091","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09091","doi":"https://doi.org/10.48550/arxiv.2610.09091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09091","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09091","pdf_url":"https://arxiv.org/pdf/2610.09091","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220996311.pdf","grobid_xml":"https://content.openalex.org/works/W7220996311.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2964121744","https://openalex.org/W2990789643","https://openalex.org/W4288726758","https://openalex.org/W7155377804"],"related_works":["https://openalex.org/W7155377804","https://openalex.org/W7167615310","https://openalex.org/W4391631420","https://openalex.org/W4405655791","https://openalex.org/W3179752900","https://openalex.org/W3170957236","https://openalex.org/W7167809691","https://openalex.org/W4416290422","https://openalex.org/W6907869874","https://openalex.org/W6948285264"],"abstract_inverted_index":{"Decision-focused":[0],"learning":[1,20,173,195],"(DFL)":[2],"trains":[3],"predictive":[4],"models":[5],"for":[6,50,76,104,117,191,201],"downstream":[7,40],"optimization,":[8],"but":[9],"existing":[10],"methods":[11,28],"largely":[12],"assume":[13],"centralized":[14],"data.":[15],"In":[16],"cross-silo":[17],"settings,":[18],"federated":[19,27,78,154,172,202],"offers":[21],"a":[22,73,83,188,198],"natural":[23],"alternative,":[24],"yet":[25],"standard":[26,153],"optimize":[29],"prediction":[30],"over":[31],"decision":[32,90,100,107,194],"quality":[33],"and":[34,68,102,112,133,139,156,164,174,180,196],"do":[35],"not":[36],"address":[37],"heterogeneity":[38,46,126,179],"in":[39,55,62],"objectives":[41],"or":[42],"feasible":[43],"sets.":[44],"This":[45],"is":[47,187],"especially":[48],"challenging":[49],"DFL":[51,175],"because":[52],"small":[53],"perturbations":[54],"polyhedral":[56],"problems":[57],"can":[58],"cause":[59],"discontinuous":[60],"changes":[61],"optimal":[63],"decisions,":[64],"destabilizing":[65],"client":[66],"updates":[67],"aggregation.":[69],"We":[70,94,122],"propose":[71],"FedRSPO+,":[72],"heterogeneity-aware":[74,199],"framework":[75],"decision-focused":[77],"learning,":[79],"built":[80],"on":[81,130,160],"RSPO+,":[82],"regularized":[84,106],"predict-then-optimize":[85],"surrogate":[86],"that":[87,96,128,185],"smooths":[88],"the":[89,105,118],"map":[91],"through":[92],"projection.":[93],"show":[95],"RSPO+":[97],"upper":[98],"bounds":[99,127],"error":[101],"regret":[103],"and,":[108],"under":[109,177],"exact":[110],"regularization":[111],"consistent":[113],"LP":[114,120],"solution":[115],"selection,":[116],"original":[119],"decision.":[121],"further":[123],"derive":[124],"cross-client":[125],"depend":[129],"both":[131],"objective":[132],"feasible-set":[134],"heterogeneity,":[135],"vanish":[136],"at":[137],"homogeneity,":[138],"require":[140],"no":[141],"strong":[142],"convexity.":[143],"FedRSPO+":[144],"uses":[145],"an":[146],"annealed,":[147],"modular":[148],"training":[149],"procedure":[150],"compatible":[151],"with":[152],"personalization":[155],"aggregation":[157],"methods.":[158],"Experiments":[159],"synthetic":[161],"knapsack,":[162],"shortest-path,":[163],"real-world":[165],"energy":[166],"pricing":[167],"tasks":[168],"compare":[169],"against":[170],"prediction-only":[171],"baselines":[176],"varying":[178],"communication":[181],"budgets.":[182],"Results":[183],"suggest":[184],"smoothing":[186],"useful":[189],"ingredient":[190],"stable":[192],"collaborative":[193],"provide":[197],"foundation":[200],"DFL.":[203]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}