{"id":"https://openalex.org/W4411639946","doi":"https://doi.org/10.1109/tkde.2025.3583059","title":"DeepNM: Incremental Graph Matching Based on Sinkhorn Similarity","display_name":"DeepNM: Incremental Graph Matching Based on Sinkhorn Similarity","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411639946","doi":"https://doi.org/10.1109/tkde.2025.3583059"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2025.3583059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3583059","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101351877","display_name":"Yikuan Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yikuan Xia","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084919879","display_name":"J.M. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazun Chen","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056666001","display_name":"Xinchi Li","orcid":"https://orcid.org/0000-0003-2456-7928"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchi Li","raw_affiliation_strings":["Big data and Artificial Intelligence, China Telecom Research Institute, Changping, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Big data and Artificial Intelligence, China Telecom Research Institute, Changping, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Gao","orcid":"https://orcid.org/0000-0002-6750-8496"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Gao","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies, CS, Peking University, Hai Dian Qu, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101351877"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8037294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"37","issue":"9","first_page":"5141","last_page":"5157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9995999932289124,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8069928884506226},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.543157696723938},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4898068606853485},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43533551692962646},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37313762307167053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2888568043708801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12419319152832031},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07328605651855469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069928884506226},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.543157696723938},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4898068606853485},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43533551692962646},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37313762307167053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2888568043708801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12419319152832031},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07328605651855469},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3583059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3583059","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7464771943","display_name":null,"funder_award_id":"62272008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W34399546","https://openalex.org/W1777560676","https://openalex.org/W1865107109","https://openalex.org/W2044490483","https://openalex.org/W2056124433","https://openalex.org/W2102086994","https://openalex.org/W2113367658","https://openalex.org/W2117831564","https://openalex.org/W2129406249","https://openalex.org/W2156543375","https://openalex.org/W2289831356","https://openalex.org/W2391555403","https://openalex.org/W2419507445","https://openalex.org/W2478722229","https://openalex.org/W2519887557","https://openalex.org/W2799132636","https://openalex.org/W2888657195","https://openalex.org/W2890187992","https://openalex.org/W2907492528","https://openalex.org/W2931335216","https://openalex.org/W2955238243","https://openalex.org/W2962756421","https://openalex.org/W2964418074","https://openalex.org/W3030424116","https://openalex.org/W3038743309","https://openalex.org/W3039701618","https://openalex.org/W3111851097","https://openalex.org/W3158091578","https://openalex.org/W3208550520","https://openalex.org/W4224316123","https://openalex.org/W4251358674","https://openalex.org/W4300672471","https://openalex.org/W4306317785","https://openalex.org/W4385284171","https://openalex.org/W4385444726","https://openalex.org/W6631190155","https://openalex.org/W6637106369","https://openalex.org/W6638373262","https://openalex.org/W6682962330","https://openalex.org/W6731581786","https://openalex.org/W6731785350","https://openalex.org/W6741832134","https://openalex.org/W6754929296","https://openalex.org/W6760001035","https://openalex.org/W6762003241","https://openalex.org/W6766978945","https://openalex.org/W6771376659","https://openalex.org/W6787995345","https://openalex.org/W6796013929"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Graph":[0,196],"matching":[1,24,116,147,190,197,221,291,317,323,369,375],"is":[2,162,184,198,338],"a":[3,76,96,124,145,199,245,282,300,304,312,316,393],"critical":[4,200],"task":[5,201],"with":[6,18,186,202,215,365],"diverse":[7,203],"real-world":[8,177,204,359],"applications.":[9,205],"Present":[10],"cutting-edge":[11,207],"methodologies":[12,208],"incorporate":[13,209],"graph":[14,31,146,189,322,351,368],"neural":[15,32],"architectures":[16,33],"combined":[17,214],"incremental":[19,48,109,188,216,350,367],"anchor":[20,49,73,105,168,217,254,344],"refinement,":[21,218],"calculating":[22,219],"the":[23,53,91,100,108,120,135,138,187,220,228,240,250,257,260,264,271,321,329,347,366,384,398,412],"similarity":[25,65,136,155,222,230,302,400],"directly":[26,223],"via":[27,224],"node":[28,225,290],"embeddings.":[29,226],"The":[30],"provide":[34,380],"enhanced":[35],"encoding":[36],"of":[37,57,63,71,84,93,102,140,242,262,349,409],"both":[38,174,311],"structural":[39],"and":[40,47,176,192,259,315,358,396],"attribute":[41],"information,":[42],"yielding":[43],"more":[44,163],"accurate":[45],"results,":[46],"refinement":[50,110],"contributes":[51],"to":[52,74,81,132,165,266,275,288,320,341,387],"overall":[54],"low":[55],"complexity":[56],"these":[58,277],"methods.":[59],"However,":[60,227],"this":[61,154,279],"method":[62,283],"direct":[64,229],"calculation":[66],"expects":[67],"all":[68,82],"neighboring":[69],"nodes":[70,94,243],"one":[72],"bear":[75],"resemblance":[77],"in":[78,256,392,405],"their":[79,294],"embeddings":[80,235],"neighbors":[83,379],"its":[85],"counterpart.":[86],"This":[87],"requirement":[88],"might":[89],"obscure":[90,239],"distinctiveness":[92,241],"within":[95,244,346],"localized":[97,246],"region.":[98,247],"Moreover,":[99],"integration":[101],"incorrectly":[103],"identified":[104,167,343],"pairs":[106,255,345],"during":[107],"process":[111],"can":[112],"significantly":[113],"degrade":[114],"subsequent":[115],"performance.":[117,195,272],"To":[118],"tackle":[119,276],"challenges,":[121,278],"we":[122,151,326],"introduce":[123],"novel":[125],"method,":[126],"Deep":[127],"Neighbor":[128],"Matching":[129],"(DeepNM),":[130],"designed":[131],"explicitly":[133],"measure":[134],"between":[137],"neighborhoods":[139],"nodes,":[141],"thereby":[142],"functioning":[143],"as":[144,310],"training":[148,313],"loss.":[149],"Further,":[150],"demonstrate":[152,327,361],"that":[153,182,328,362],"measurement,":[156],"based":[157,232,292],"on":[158,173,233,293,303,334,356,401],"common":[159,335,378],"neighbor":[160,336],"statistics,":[161,337],"resilient":[164,340],"inaccurately":[166,342],"pairs.":[169],"Our":[170,353],"comprehensive":[171,354],"experiments":[172,355],"synthetic":[175,357],"datasets":[178,360],"offer":[179],"empirical":[180],"evidence":[181],"DeepNM":[183,298,385],"compatible":[185,364],"paradigm":[191],"has":[193],"outstanding":[194],"Current":[206],"GNN":[210,237],"(Graph":[211],"Neural":[212],"Network)":[213],"computation":[231],"aggregated":[234],"from":[236],"may":[238,268],"In":[248,273],"addition,":[249],"possible":[251],"wrongly":[252],"added":[253],"iterations":[258],"lack":[261],"capturing":[263],"relationships":[265],"anchors":[267],"further":[269],"affect":[270],"order":[274],"paper":[280],"proposes":[281],"named":[284],"DeepNM,":[285,363],"which":[286,308,332],"attempts":[287],"find":[289],"neighbors'":[295],"similarities.":[296],"Specifically,":[297],"introduces":[299],"Sinkhorn-based":[301,330],"node's":[305],"neighborhood's":[306],"embeddings,":[307],"serves":[309],"loss":[314],"metric":[318],"tailored":[319],"problem.":[324],"Additionally,":[325],"similarity,":[331],"relies":[333],"highly":[339],"context":[348],"matching.":[352],"paradigm,":[370],"excels":[371],"particularly":[372],"well":[373],"at":[374],"graphs":[376,403],"where":[377],"good":[381],"matches.":[382],"Applying":[383],"pipeline":[386],"real":[388],"social":[389],"networks":[390],"results":[391,404],"6%":[394],"improvement,":[395],"applying":[397],"Sinkhorn":[399],"knowledge":[402],"an":[406],"average":[407],"improvement":[408],"1.7%":[410],"over":[411],"best":[413],"baseline.":[414]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}