{"id":"https://openalex.org/W4414110704","doi":"https://doi.org/10.1109/access.2025.3608236","title":"Enhancing Entity Resolution Through Graph-Based Data Augmentation and Label Noise Identification","display_name":"Enhancing Entity Resolution Through Graph-Based Data Augmentation and Label Noise Identification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414110704","doi":"https://doi.org/10.1109/access.2025.3608236"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3608236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3608236","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3608236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099433312","display_name":"Tobias Rettenmeier","orcid":"https://orcid.org/0009-0002-7946-2031"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Rettenmeier","raw_affiliation_strings":["Institute for Intelligent Cyber-Physical Systems, Heilbronn University of Applied Sciences, Künzelsau, Germany"],"raw_orcid":"https://orcid.org/0009-0002-7946-2031","affiliations":[{"raw_affiliation_string":"Institute for Intelligent Cyber-Physical Systems, Heilbronn University of Applied Sciences, Künzelsau, Germany","institution_ids":["https://openalex.org/I41121874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075009378","display_name":"Alexander Jesser","orcid":"https://orcid.org/0000-0003-2067-6860"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Jesser","raw_affiliation_strings":["Institute for Intelligent Cyber-Physical Systems, Heilbronn University of Applied Sciences, Künzelsau, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2067-6860","affiliations":[{"raw_affiliation_string":"Institute for Intelligent Cyber-Physical Systems, Heilbronn University of Applied Sciences, Künzelsau, Germany","institution_ids":["https://openalex.org/I41121874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5421,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86086204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"161134","last_page":"161149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.994700014591217,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.621999979019165},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5706999897956848},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4986000061035156},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42739999294281006},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41600000858306885},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3995000123977661},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.3815000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540999889373779},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6165000200271606},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041999816894531},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3995000123977661},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.3815000057220459},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3608236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3608236","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:30b30bf5a94b41bba66f41ddfb837124","is_oa":true,"landing_page_url":"https://doaj.org/article/30b30bf5a94b41bba66f41ddfb837124","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 161134-161149 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3608236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3608236","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1964786778","https://openalex.org/W1999294550","https://openalex.org/W2007682403","https://openalex.org/W2045968013","https://openalex.org/W2062340526","https://openalex.org/W2107966677","https://openalex.org/W2118924197","https://openalex.org/W2164456230","https://openalex.org/W2794573079","https://openalex.org/W2896457183","https://openalex.org/W2945883855","https://openalex.org/W2952205826","https://openalex.org/W3014705052","https://openalex.org/W3021217443","https://openalex.org/W3042609801","https://openalex.org/W3146259567","https://openalex.org/W3174036215","https://openalex.org/W3175103763","https://openalex.org/W3202190154","https://openalex.org/W4221163653","https://openalex.org/W4295768363","https://openalex.org/W4324144712","https://openalex.org/W4399952756","https://openalex.org/W4400527373","https://openalex.org/W4411556380"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W1517180214","https://openalex.org/W2082780921","https://openalex.org/W2025517136","https://openalex.org/W1972473893","https://openalex.org/W2466435674","https://openalex.org/W2765200542"],"abstract_inverted_index":{"Entity":[0],"resolution":[1,70],"is":[2,30,57,85,137],"an":[3],"important":[4],"task":[5],"in":[6],"data":[7,10,23,46,58,112,146,168],"integration":[8],"and":[9,25,43,62,95,181,211,219,225],"cleaning.":[11],"This":[12],"study":[13,193],"explores":[14],"how":[15],"graph-based":[16,54,201,223],"techniques":[17],"can":[18,113],"address":[19],"the":[20,53,108,127,134,157,166,176,217],"challenges":[21],"of":[22,52,83,110,119,143,156,165,187,191,216,222],"availability":[24],"label":[26,77,124,132],"quality.":[27],"An":[28],"approach":[29],"formalized":[31],"that":[32,56],"leverages":[33],"graph":[34],"theory":[35],"to":[36,67,139,174,182],"enhance":[37],"entity-resolution":[38,208],"performance":[39,218],"by":[40,116],"augmenting":[41],"datasets":[42,71],"identifying":[44,131],"mislabeled":[45],"points.":[47,147,169],"To":[48],"evaluate":[49],"three":[50],"methods":[51,88,128,180],"approach,":[55],"augmentation,":[59,202],"consistency":[60,135],"check,":[61],"loss-outlier":[63],"detection,":[64],"a":[65,117,205],"framework":[66,94,206],"generate":[68],"entity":[69],"with":[72],"varying":[73],"properties":[74],"such":[75],"as":[76,104],"noise,":[78,133],"class":[79],"distribution,":[80],"or":[81],"amount":[82,109],"entities":[84],"developed.":[86],"The":[87,100,148,189],"are":[89,103,172],"then":[90],"evaluated":[91],"using":[92],"this":[93,161,192],"ten":[96],"different":[97],"real-world":[98],"datasets.":[99],"main":[101],"findings":[102],"follows:":[105],"On":[106],"average,":[107],"usable":[111],"be":[114],"increased":[115],"factor":[118],"2.5":[120],"without":[121],"introducing":[122],"additional":[123],"noise.":[125],"Among":[126],"aimed":[129],"at":[130],"check":[136],"able":[138],"detect":[140],"approximately":[141],"16%":[142],"incorrectly":[144],"labeled":[145],"loss-based":[149],"outlier":[150],"detection":[151],"method":[152],"removes":[153],"about":[154],"26%":[155],"false":[158],"labels,":[159],"although":[160],"entails":[162],"discarding":[163],"10%":[164],"overall":[167],"Further":[170],"analyses":[171],"conducted":[173],"investigate":[175],"factors":[177,221],"influencing":[178,220],"these":[179],"better":[183],"understand":[184],"their":[185],"mechanisms":[186],"action.":[188],"contributions":[190],"include:":[194],"(1)":[195],"formalizing":[196],"previous":[197],"preliminary":[198],"work":[199],"on":[200],"(2)":[203],"developing":[204],"for":[207],"dataset":[209],"generation,":[210],"(3)":[212],"providing":[213],"in-depth":[214],"evaluation":[215],"augmentation":[224],"label-noise":[226],"identification.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}