{"id":"https://openalex.org/W7160850319","doi":"https://doi.org/10.48550/arxiv.2605.07113","title":"Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks","display_name":"Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160850319","doi":"https://doi.org/10.48550/arxiv.2605.07113"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07113","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07113","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135850879","display_name":"Hao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135851556","display_name":"Chendi Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Chendi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135830435","display_name":"Christopher Morris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morris, Christopher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135902698","display_name":"Andrea Lodi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lodi, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135883979","display_name":"Can Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2872999906539917,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2872999906539917,"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.2786000072956085,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.12250000238418579,"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/bounding-overwatch","display_name":"Bounding overwatch","score":0.6974999904632568},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6398000121116638},{"id":"https://openalex.org/keywords/semidefinite-programming","display_name":"Semidefinite programming","score":0.5728999972343445},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43290001153945923},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.41100001335144043},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.39649999141693115},{"id":"https://openalex.org/keywords/branch-and-bound","display_name":"Branch and bound","score":0.39640000462532043}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6974999904632568},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5837000012397766},{"id":"https://openalex.org/C101901036","wikidata":"https://www.wikidata.org/wiki/Q2269096","display_name":"Semidefinite programming","level":2,"score":0.5728999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5612999796867371},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C93693863","wikidata":"https://www.wikidata.org/wiki/Q897659","display_name":"Branch and bound","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C52692508","wikidata":"https://www.wikidata.org/wiki/Q1333872","display_name":"Combinatorial optimization","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32589998841285706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07113","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07113","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Exact":[0],"solution":[1],"of":[2,81,133,157],"hard":[3],"combinatorial":[4],"optimization":[5,164],"problems":[6],"often":[7],"relies":[8],"on":[9],"strong":[10],"convex":[11,167],"relaxations,":[12],"but":[13],"solving":[14,138],"these":[15,62],"relaxations":[16,42,119],"repeatedly":[17],"inside":[18],"a":[19,48,56,112],"branch-and-bound":[20,73],"algorithm":[21],"can":[22,66,128],"be":[23,67],"prohibitively":[24],"expensive.":[25],"Hence,":[26],"we":[27,123],"consider":[28],"this":[29],"challenge":[30],"for":[31,61,161],"Max-Cut,":[32],"where":[33],"branch":[34],"and":[35,65,86,90],"bound":[36,44],"commonly":[37],"uses":[38],"semidefinite":[39],"programming":[40],"(SDP)":[41],"to":[43,141],"subproblems.":[45],"We":[46],"propose":[47],"Max-Cut-specific":[49],"graph":[50],"neural":[51,59],"network":[52],"that":[53,125],"serves":[54],"as":[55,120],"principled,":[57],"lightweight":[58],"proxy":[60],"SDP":[63,92,96,118,149],"solvers":[64],"plugged":[68],"directly":[69],"into":[70],"an":[71],"exact":[72,136,163],"framework.":[74],"The":[75,94],"proposed":[76],"architecture":[77,127],"has":[78],"update":[79],"steps":[80],"complexity":[82],"$\\mathcal{O}(n^2":[83],"+":[84],"ne)$,":[85],"predicts":[87],"both":[88],"primal-":[89],"dual-feasible":[91],"solutions.":[93],"primal":[95],"solutions":[97,101],"yield":[98],"feasible":[99],"Max-Cut":[100,137],"via":[102],"the":[103,131,147,155],"Goemans--Williamson":[104],"algorithm.":[105],"In":[106],"addition,":[107],"it":[108],"is":[109],"trained":[110],"in":[111,135],"self-supervised":[113],"fashion":[114],"without":[115],"requiring":[116],"solved":[117],"labels.":[121],"Empirically,":[122],"show":[124],"our":[126],"substantially":[129],"reduce":[130],"cost":[132],"bounding":[134],"by":[139],"up":[140],"$10.6":[142],"\\times$":[143],"compared":[144],"with":[145],"using":[146],"state-of-the-art":[148],"solver":[150],"Mosek.":[151],"Our":[152],"work":[153],"highlights":[154],"potential":[156],"learned,":[158],"validity-preserving":[159],"surrogates":[160],"accelerating":[162],"over":[165],"structured":[166],"relaxations.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}