{"id":"https://openalex.org/W4205196528","doi":"https://doi.org/10.1109/tkde.2021.3134806","title":"CollaborEM: A Self-Supervised Entity Matching Framework Using Multi-Features Collaboration","display_name":"CollaborEM: A Self-Supervised Entity Matching Framework Using Multi-Features Collaboration","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4205196528","doi":"https://doi.org/10.1109/tkde.2021.3134806"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3134806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3134806","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":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/8341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088891882","display_name":"Congcong Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congcong Ge","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399544","display_name":"Pengfei Wang","orcid":"https://orcid.org/0000-0001-9992-1464"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wang","raw_affiliation_strings":["School of Software, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9992-1464","affiliations":[{"raw_affiliation_string":"School of Software, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432093","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-5685-7017"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063552937","display_name":"Xiaoze Liu","orcid":"https://orcid.org/0000-0002-9726-3397"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoze Liu","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050328715","display_name":"Baihua Zheng","orcid":"https://orcid.org/0000-0001-9792-9171"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Baihua Zheng","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9792-9171","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-3816-8450","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5013,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85824609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"35","issue":"12","first_page":"12139","last_page":"12152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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/tuple","display_name":"Tuple","score":0.9345145225524902},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.7032812833786011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.653579592704773},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6274183392524719},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4816509783267975},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44508737325668335},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.42530614137649536},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4208638668060303},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4003525376319885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37239354848861694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35839998722076416},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34469759464263916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2180837094783783},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1250762939453125}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.9345145225524902},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.7032812833786011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.653579592704773},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6274183392524719},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4816509783267975},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44508737325668335},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.42530614137649536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4208638668060303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4003525376319885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37239354848861694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34469759464263916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2180837094783783},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1250762939453125},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2021.3134806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3134806","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"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-9344","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/8341","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TKDE.2021.3134806","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-9344","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/8341","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TKDE.2021.3134806","raw_type":"Journal Article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5410940137","display_name":null,"funder_award_id":"62025206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5916212369","display_name":"\u53cdTop-k\u7a7a\u95f4\u5173\u952e\u5b57\u67e5\u8be2\u53ef\u7528\u6027\u7814\u7a76","funder_award_id":"61972338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6456106688","display_name":null,"funder_award_id":"62102351","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":77,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W1964786778","https://openalex.org/W1981590391","https://openalex.org/W2056748234","https://openalex.org/W2099637074","https://openalex.org/W2107966677","https://openalex.org/W2145492473","https://openalex.org/W2164625277","https://openalex.org/W2432356473","https://openalex.org/W2542998387","https://openalex.org/W2609368435","https://openalex.org/W2612177096","https://openalex.org/W2775696413","https://openalex.org/W2786088545","https://openalex.org/W2790814121","https://openalex.org/W2798649495","https://openalex.org/W2804269561","https://openalex.org/W2808284704","https://openalex.org/W2896457183","https://openalex.org/W2907492528","https://openalex.org/W2946297661","https://openalex.org/W2946504770","https://openalex.org/W2949434543","https://openalex.org/W2951147191","https://openalex.org/W2964015378","https://openalex.org/W2966720878","https://openalex.org/W2970597249","https://openalex.org/W2970641574","https://openalex.org/W2970921796","https://openalex.org/W2971681342","https://openalex.org/W2980282514","https://openalex.org/W2997169693","https://openalex.org/W3010144884","https://openalex.org/W3011807731","https://openalex.org/W3012000912","https://openalex.org/W3012733951","https://openalex.org/W3014705052","https://openalex.org/W3021217443","https://openalex.org/W3029701880","https://openalex.org/W3034616364","https://openalex.org/W3075591326","https://openalex.org/W3081497074","https://openalex.org/W3098038527","https://openalex.org/W3101056714","https://openalex.org/W3103177583","https://openalex.org/W3104570147","https://openalex.org/W3106020963","https://openalex.org/W3122741928","https://openalex.org/W3123375411","https://openalex.org/W3128590588","https://openalex.org/W3177179246","https://openalex.org/W4242744113","https://openalex.org/W4254788633","https://openalex.org/W4293320219","https://openalex.org/W4294170691","https://openalex.org/W4294558607","https://openalex.org/W4295312788","https://openalex.org/W4295838474","https://openalex.org/W4297733535","https://openalex.org/W6640425456","https://openalex.org/W6682691769","https://openalex.org/W6718112784","https://openalex.org/W6726873649","https://openalex.org/W6729767818","https://openalex.org/W6738964360","https://openalex.org/W6745537798","https://openalex.org/W6748102297","https://openalex.org/W6748848838","https://openalex.org/W6755207826","https://openalex.org/W6758075616","https://openalex.org/W6762814303","https://openalex.org/W6763701032","https://openalex.org/W6766978945","https://openalex.org/W6768817161","https://openalex.org/W6771626834","https://openalex.org/W6774394432","https://openalex.org/W6797672499"],"related_works":["https://openalex.org/W2143551613","https://openalex.org/W4245395944","https://openalex.org/W1979740464","https://openalex.org/W2138823233","https://openalex.org/W2143345456","https://openalex.org/W2023236823","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W2101053337","https://openalex.org/W2504004674"],"abstract_inverted_index":{"Entity":[0],"Matching":[1],"(EM)":[2],"aims":[3],"to":[4,10,18,25,45,52,63,131,172,213],"identify":[5],"whether":[6],"two":[7,34,38,112],"tuples":[8,36,185],"refer":[9],"the":[11,30,125,148,152,158,162,166,174,202,214],"same":[12],"real-world":[13,192],"entity":[14,78],"and":[15,97,119,139,155,181,207],"is":[16,22,85,129,170,208],"well-known":[17],"be":[19],"labor-intensive.":[20],"It":[21,84],"a":[23,76,104,133,140],"prerequisite":[24],"anomaly":[26],"detection,":[27],"as":[28],"comparing":[29],"attribute":[31],"values":[32],"of":[33,87,111,135,142,151,161,184],"matched":[35],"from":[37],"different":[39],"datasets":[40],"provides":[41],"one":[42],"effective":[43],"way":[44],"detect":[46],"anomalies.":[47],"Existing":[48],"EM":[49,91,121,193,205,217],"approaches,":[50],"due":[51],"insufficient":[53],"feature":[54],"discovery":[55],"or":[56,210],"error-prone":[57],"inherent":[58],"characteristics,":[59],"are":[60],"not":[61],"able":[62],"achieve":[64],"stable":[65],"performance.":[66],"In":[67,124,165],"this":[68],"paper,":[69],"we":[70],"present":[71],"<inline-formula><tex-math":[72,107,197],"notation=\"LaTeX\">${{\\sf":[73,108,198],"CollaborEM}}$</tex-math></inline-formula>":[74,109,199],",":[75],"self-supervised":[77],"matching":[79,175],"framework":[80],"via":[81],"multi-features":[82],"collaboration.":[83],"capable":[86],"(i)":[88],"obtaining":[89],"reliable":[90],"results":[92,189],"with":[93],"zero":[94],"human":[95],"annotations":[96],"(ii)":[98],"discovering":[99,178],"adequate":[100],"tuples\u2019":[101],"features":[102,180,183],"in":[103],"fault-tolerant":[105],"manner.":[106],"consists":[110],"phases,":[113],"i.e.,":[114],"automatic":[115],"label":[116],"generation":[117],"(ALG)":[118],"collaborative":[120],"training":[122,159],"(CEMT).":[123],"first":[126],"phase,":[127,168],"ALG":[128,146],"proposed":[130],"generate":[132],"set":[134,141],"positive":[136],"tuple":[137,144],"pairs":[138],"negative":[143],"pairs.":[145],"guarantees":[147],"high":[149],"quality":[150,160],"generated":[153],"tuples,":[154],"hence":[156],"ensures":[157],"subsequent":[163],"CEMT.":[164],"second":[167],"CEMT":[169],"introduced":[171],"learn":[173],"signals":[176],"by":[177],"graph":[179],"sentence":[182],"collaboratively.":[186],"Extensive":[187],"experimental":[188],"over":[190],"eight":[191],"benchmarks":[194],"show":[195],"that":[196],"outperforms":[200],"all":[201],"existing":[203],"unsupervised":[204],"approaches":[206],"comparable":[209],"even":[211],"superior":[212],"state-of-the-art":[215],"supervised":[216],"methods.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}