{"id":"https://openalex.org/W7214716625","doi":"https://doi.org/10.48550/arxiv.2609.32661","title":"Equivariant Neural Primal-Dual Assignment for Maximum Common Edge Subgraphs","display_name":"Equivariant Neural Primal-Dual Assignment for Maximum Common Edge Subgraphs","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214716625","doi":"https://doi.org/10.48550/arxiv.2609.32661"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32661","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32661","pdf_url":"https://arxiv.org/pdf/2609.32661","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":"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/2609.32661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153413138","display_name":"Jiaqing Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jiaqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153546030","display_name":"Yanchao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yanchao","raw_affiliation_strings":["Nanjing University","Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153525567","display_name":"Zhuo Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zhuo","raw_affiliation_strings":["Shanghai Innovation Institute","Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]},{"raw_affiliation_string":"Southeast University","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153440158","display_name":"Yuxin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yuxin","raw_affiliation_strings":["Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114063871","display_name":"Tianfan Fu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Tianfan","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153428216","display_name":"Yuqiang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yuqiang","raw_affiliation_strings":["Nanjing University","Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.028699999675154686,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11476","display_name":"Graph theory and applications","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-matching","display_name":"graph matching","score":0.9079999923706055},{"id":"https://openalex.org/keywords/equivariant-neural-networks","display_name":"equivariant neural networks","score":0.7749999761581421},{"id":"https://openalex.org/keywords/hungarian-algorithm","display_name":"Hungarian algorithm","score":0.8870000243186951},{"id":"https://openalex.org/keywords/molecular-similarity-search","display_name":"molecular similarity search","score":0.8029999732971191},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.460999995470047},{"id":"https://openalex.org/keywords/graph-isomorphism","display_name":"graph isomorphism","score":0.5519999861717224}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5008999705314636},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41130000352859497},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C53052385","wikidata":"https://www.wikidata.org/wiki/Q17104046","display_name":"Mixed graph","level":5,"score":0.32100000977516174},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C128115575","wikidata":"https://www.wikidata.org/wiki/Q5597083","display_name":"Graph factorization","level":5,"score":0.31949999928474426},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C182964748","wikidata":"https://www.wikidata.org/wiki/Q208216","display_name":"Triangle inequality","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C102408133","wikidata":"https://www.wikidata.org/wiki/Q5156350","display_name":"Competitive analysis","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32661","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32661","pdf_url":"https://arxiv.org/pdf/2609.32661","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.32661","doi":"https://doi.org/10.48550/arxiv.2609.32661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32661","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:2609.32661","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32661","pdf_url":"https://arxiv.org/pdf/2609.32661","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214716625.pdf","grobid_xml":"https://content.openalex.org/works/W7214716625.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1988622494","https://openalex.org/W2036996178","https://openalex.org/W3038203542","https://openalex.org/W3042313988","https://openalex.org/W3158330599","https://openalex.org/W3170435764","https://openalex.org/W4389775223","https://openalex.org/W4391255631","https://openalex.org/W4394783297"],"related_works":["https://openalex.org/W206244425","https://openalex.org/W4417300533","https://openalex.org/W7098179476","https://openalex.org/W25719913","https://openalex.org/W7101264299","https://openalex.org/W1977149746","https://openalex.org/W6903846798","https://openalex.org/W4407318488","https://openalex.org/W3175773592","https://openalex.org/W7204465018"],"abstract_inverted_index":{"Maximum":[0],"common":[1],"edge":[2],"subgraph":[3],"(MCES)":[4],"matching":[5,27,64,161],"finds":[6],"a":[7,47,62,89,129,133,168],"partial":[8,134],"vertex":[9],"correspondence":[10],"between":[11],"two":[12],"labeled":[13,19],"graphs":[14],"that":[15,108,141],"preserves":[16],"as":[17,21],"many":[18,28],"edges":[20],"possible.":[22],"Molecular":[23],"similarity":[24],"search":[25],"requires":[26],"graph":[29,152],"pairs,":[30],"making":[31],"the":[32,122,154,159,174,178,212,231,245,251,268],"cost":[33,87],"of":[34,80,192,225,230],"repeated":[35],"queries":[36,76],"important.":[37],"The":[38,93],"strongest":[39],"baseline":[40],"attains":[41],"accurate":[42],"MCES":[43,170],"solutions":[44],"but":[45],"trains":[46],"separate":[48],"network":[49,145],"for":[50,99,143,190],"each":[51],"pair.":[52],"We":[53,137],"introduce":[54],"Equivariant":[55],"Neural":[56],"Primal-Dual":[57],"Assignment":[58],"(ENPDA),":[59],"which":[60],"learns":[61,103],"shared":[63],"policy":[65,94,246],"and":[66,83,102,105,128,156,164,215,242],"applies":[67],"it":[68],"to":[69,115,237],"new":[70],"pairs":[71],"without":[72,235],"further":[73],"training,":[74],"answering":[75],"roughly":[77],"three":[78,198,272],"orders":[79],"magnitude":[81],"faster":[82],"recovering":[84],"its":[85],"training":[86],"after":[88,222],"few":[90],"dozen":[91],"queries.":[92],"recomputes":[95],"exact":[96,148],"objective":[97],"marginals":[98],"candidate":[100],"matches":[101],"corrections":[104],"step":[106],"sizes":[107],"update":[109,126,214],"their":[110],"scores.":[111],"Target":[112],"prices":[113,166],"respond":[114],"competition":[116],"when":[117],"several":[118],"source":[119],"vertices":[120],"favor":[121],"same":[123,213],"target.":[124],"Four":[125],"rounds":[127],"Hungarian":[130],"projection":[131,216],"produce":[132],"one-to-one":[135],"matching.":[136],"prove":[138,187],"per-pair":[139],"guarantees":[140],"hold":[142],"any":[144],"parameters.":[146],"In":[147],"arithmetic,":[149],"reordering":[150],"either":[151],"permutes":[153],"assignment":[155],"price":[157],"states,":[158],"projected":[160],"is":[162],"one-to-one,":[163],"repaired":[165],"give":[167],"valid":[169],"upper":[171],"bound.":[172],"Subtracting":[173],"preserved-edge":[175],"count":[176],"bounds":[177],"optimality":[179,189],"gap;":[180],"combined":[181],"with":[182,201,211],"structural":[183],"caps,":[184],"these":[185],"certificates":[186],"global":[188],"60":[191],"291":[193],"native":[194],"test":[195],"pairs.":[196],"On":[197],"molecular":[199],"benchmarks":[200],"disjoint":[202],"train/validation/test":[203],"splits,":[204],"ENPDA":[205,262],"improves":[206],"over":[207,250],"an":[208],"analytic":[209,252],"counterpart":[210],"budget":[217],"by":[218],"7.4-8.6":[219],"accuracy":[220],"points;":[221],"one":[223],"second":[224],"refinement":[226],"search,":[227],"2.5-3":[228],"points":[229,249],"gain":[232],"remain.":[233],"Transferred":[234],"fine-tuning":[236],"edge-deletion":[238],"tasks":[239],"from":[240],"social":[241],"protein":[243],"graphs,":[244],"gains":[247],"9.1-17.6":[248],"counterpart.":[253],"When":[254],"output":[255],"matchings":[256],"must":[257],"keep":[258],"aromatic":[259],"rings":[260],"intact,":[261],"recovers":[263],"more":[264],"reference":[265],"bonds":[266],"than":[267],"baselines":[269],"on":[270],"all":[271],"datasets.":[273]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}