{"id":"https://openalex.org/W7164818151","doi":"https://doi.org/10.1145/3805622.3810682","title":"Robust Graph Matching via Confidence-Guided Distillation and Random Node Masking","display_name":"Robust Graph Matching via Confidence-Guided Distillation and Random Node Masking","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164818151","doi":"https://doi.org/10.1145/3805622.3810682"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810682","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100297210","display_name":"Zhoubo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoubo Xu","raw_affiliation_strings":["Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0009-4948-4599","affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138688533","display_name":"Zizhao Pang","orcid":"https://orcid.org/0000-0002-0609-8024"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizhao Pang","raw_affiliation_strings":["Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0002-0609-8024","affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770786","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-2554-2888"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Meng","raw_affiliation_strings":["Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0003-7548-5532","affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138666126","display_name":"Huijie Cong","orcid":"https://orcid.org/0009-0006-3960-062X"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijie Cong","raw_affiliation_strings":["Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0006-3960-062X","affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93510129,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.5022000074386597,"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":0.5022000074386597,"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":0.4431000053882599,"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/T11719","display_name":"Data Quality and Management","score":0.0215000007301569,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5758000016212463},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4691999852657318},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4661000072956085},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.43709999322891235},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.43050000071525574},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3750999867916107},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021999955177307},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46939998865127563},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C72545166","wikidata":"https://www.wikidata.org/wiki/Q10866593","display_name":"3-dimensional matching","level":4,"score":0.29339998960494995},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7845286726951599,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1587878450","https://openalex.org/W1677409904","https://openalex.org/W1857884451","https://openalex.org/W1990283121","https://openalex.org/W2031489346","https://openalex.org/W2032558547","https://openalex.org/W2077069816","https://openalex.org/W2141362318","https://openalex.org/W2142726150","https://openalex.org/W2151103935","https://openalex.org/W2166820607","https://openalex.org/W2471962767","https://openalex.org/W2535410496","https://openalex.org/W2768308213","https://openalex.org/W2799132636","https://openalex.org/W2931335216","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3034659318","https://openalex.org/W3035524453","https://openalex.org/W3039701618","https://openalex.org/W3099546855","https://openalex.org/W3170435764","https://openalex.org/W4290876361","https://openalex.org/W4312272410","https://openalex.org/W4312576456","https://openalex.org/W4312718912","https://openalex.org/W4313156423","https://openalex.org/W4313183742","https://openalex.org/W4386066138","https://openalex.org/W4386083137","https://openalex.org/W4390872216","https://openalex.org/W4399731926","https://openalex.org/W4406894845","https://openalex.org/W4411967833"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"graph":[1,41],"matching":[2,42],"has":[3],"made":[4],"notable":[5],"progress":[6],"in":[7,15,197],"recent":[8],"years;":[9],"however,":[10],"existing":[11],"models":[12],"remain":[13],"fragile":[14],"complex":[16,198],"scenarios":[17],"involving":[18],"occlusion,":[19],"drastic":[20],"viewpoint":[21],"changes,":[22],"and":[23,91,98,176,180,185,188],"missing":[24],"structures,":[25],"where":[26],"keypoint":[27],"annotations":[28],"inherently":[29],"contain":[30],"noise.":[31],"To":[32,143],"address":[33],"this":[34],"limitation,":[35],"we":[36,57,106,147],"propose":[37],"a":[38,63,68,108],"unified":[39],"robust":[40],"framework,":[43],"MaCo-GM.":[44,169],"Unlike":[45],"conventional":[46],"momentum":[47,64],"distillation":[48],"methods":[49],"that":[50,115],"primarily":[51],"operate":[52],"at":[53],"the":[54,59,76,89,100,125,166],"feature":[55],"level,":[56],"exploit":[58],"supervisory":[60],"value":[61],"of":[62,102,168],"teacher":[65],"by":[66,178,186],"designing":[67],"Teacher":[69],"Confidence-Guided":[70],"Loss":[71],"Weighting":[72],"(TCGLW)":[73],"strategy.":[74],"Specifically,":[75],"teacher\u2019s":[77],"predictions":[78],"are":[79],"converted":[80],"into":[81],"node-level":[82],"confidence":[83],"weights":[84],"to":[85,127,155],"explicitly":[86],"modulate":[87],"both":[88],"contrastive":[90],"permutation":[92],"losses,":[93],"thereby":[94],"suppressing":[95],"low-confidence":[96],"nodes":[97],"facilitating":[99],"learning":[101],"reliable":[103],"matches.":[104],"Furthermore,":[105],"introduce":[107,149],"student-side":[109],"Random":[110],"Node":[111],"Masking":[112],"(RNM)":[113],"mechanism":[114,154],"randomly":[116],"masks":[117],"node":[118],"features":[119],"before":[120],"message":[121],"passing.":[122],"This":[123],"forces":[124],"model":[126],"rely":[128],"on":[129,161,182,190],"neighborhood":[130],"consistency":[131],"for":[132],"inference":[133],"when":[134],"local":[135],"information":[136],"is":[137],"unreliable,":[138],"effectively":[139],"mitigating":[140],"noise":[141],"propagation.":[142],"balance":[144],"multi-objective":[145],"optimization,":[146],"further":[148],"an":[150],"adaptive":[151],"loss":[152],"scaling":[153],"ensure":[156],"coordinated":[157],"convergence.":[158],"Extensive":[159],"experiments":[160],"three":[162],"public":[163],"benchmarks":[164],"demonstrate":[165],"superiority":[167],"Notably,":[170],"it":[171],"outperforms":[172],"strong":[173],"baselines":[174],"COMMON":[175],"GMTR":[177],"3.2%":[179],"2.3%":[181],"Pascal":[183],"VOC,":[184],"0.7%":[187],"2.0%":[189],"SPair-71k,":[191],"respectively,":[192],"highlighting":[193],"its":[194],"significant":[195],"robustness":[196],"scenarios.":[199]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}