{"id":"https://openalex.org/W4293499245","doi":"https://doi.org/10.1109/tkde.2022.3200921","title":"Multi-Faceted Knowledge-Driven Pre-Training for Product Representation Learning","display_name":"Multi-Faceted Knowledge-Driven Pre-Training for Product Representation Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4293499245","doi":"https://doi.org/10.1109/tkde.2022.3200921"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3200921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3200921","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/A5090808794","display_name":"Denghui Zhang","orcid":"https://orcid.org/0000-0001-9602-870X"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denghui Zhang","raw_affiliation_strings":["Rutgers, The State University of New Jersey, Newark, USA"],"raw_orcid":"https://orcid.org/0000-0001-9602-870X","affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, Newark, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101594832","display_name":"Yanchi Liu","orcid":"https://orcid.org/0000-0003-4396-5139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanchi Liu","raw_affiliation_strings":["NEC Laboratories America, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049462386","display_name":"Zixuan Yuan","orcid":"https://orcid.org/0000-0003-1197-0347"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixuan Yuan","raw_affiliation_strings":["Rutgers, The State University of New Jersey, Newark, USA"],"raw_orcid":"https://orcid.org/0000-0003-1197-0347","affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, Newark, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032187620","display_name":"Yanjie Fu","orcid":"https://orcid.org/0000-0002-1767-8024"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanjie Fu","raw_affiliation_strings":["University of Central Florida, Orlando, USA"],"raw_orcid":"https://orcid.org/0000-0002-1767-8024","affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456776","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0002-1318-6583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["NEC Laboratories America, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Rutgers, The State University of New Jersey, Newark, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, Newark, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73801839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9958999752998352,"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":0.8421478271484375},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5563094019889832},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.5226690173149109},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5065885782241821},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48927614092826843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45615047216415405},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.43856045603752136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38454508781433105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10669609904289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8421478271484375},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5563094019889832},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.5226690173149109},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5065885782241821},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48927614092826843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45615047216415405},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.43856045603752136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38454508781433105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10669609904289246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3200921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3200921","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1599364940","https://openalex.org/W1888005072","https://openalex.org/W2010416066","https://openalex.org/W2154851992","https://openalex.org/W2525778437","https://openalex.org/W2542998387","https://openalex.org/W2740070748","https://openalex.org/W2767724106","https://openalex.org/W2794556650","https://openalex.org/W2798649495","https://openalex.org/W2807329228","https://openalex.org/W2884789176","https://openalex.org/W2885625746","https://openalex.org/W2889496895","https://openalex.org/W2896457183","https://openalex.org/W2945883855","https://openalex.org/W2962739339","https://openalex.org/W2962756421","https://openalex.org/W2963168538","https://openalex.org/W2964341035","https://openalex.org/W2970599813","https://openalex.org/W2970986510","https://openalex.org/W2990816204","https://openalex.org/W2997144896","https://openalex.org/W3002414756","https://openalex.org/W3011411500","https://openalex.org/W3017018726","https://openalex.org/W3025937915","https://openalex.org/W3037151198","https://openalex.org/W3098003395","https://openalex.org/W3099018151","https://openalex.org/W3101157305","https://openalex.org/W3102512871","https://openalex.org/W3104097132","https://openalex.org/W3105174509","https://openalex.org/W3105684067","https://openalex.org/W3151929433","https://openalex.org/W3167926051","https://openalex.org/W3174924631","https://openalex.org/W3175604467","https://openalex.org/W3182414949","https://openalex.org/W4300175872","https://openalex.org/W6682691769","https://openalex.org/W6684813226","https://openalex.org/W6727690538","https://openalex.org/W6739076403","https://openalex.org/W6739901393","https://openalex.org/W6753224557","https://openalex.org/W6755207826","https://openalex.org/W6776528237","https://openalex.org/W6798398338"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2088247287","https://openalex.org/W3006008237","https://openalex.org/W2140798747"],"abstract_inverted_index":{"As":[0,249],"a":[1,13,88,117,133,139,151,171,250,263,335,364,370,376,386],"key":[2,163,251],"component":[3,252],"of":[4,16,60,165,179,226,253,265,310,394,441],"e-commerce":[5,254],"computing,":[6,255],"product":[7,20,104,235,238,241,256,268,351],"representation":[8,94,257,341],"learning":[9,258],"(PRL)":[10,259],"has":[11],"benefitted":[12],"wide":[14],"range":[15],"applications,":[17,266],"such":[18],"as":[19,194,410],"matching,":[21,236,269],"search,":[22,239,270],"and":[23,102,107,124,187,240,246,271,349,354,368,403],"categorization.":[24,272],"Nonetheless,":[25],"existing":[26,48,274,296],"PRL":[27,76,275,323],"approaches":[28,276],"have":[29,222,277,437],"poor":[30,278],"language":[31,62,122,279,312],"understanding":[32,280],"ability":[33,38,281],"due":[34,282],"to":[35,72,77,116,137,160,176,208,283,286,302,319,324,363,374,391,424],"the":[36,44,57,70,79,99,162,211,224,228,292,307,317,326,346,426,439,444],"insufficient":[37],"in":[39,65,129,197,413],"capturing":[40],"contextualized":[41,288],"semantics.":[42,289],"Also,":[43],"learned":[45,293],"representations":[46,294],"by":[47,56,190,295,306,406],"methods":[49,297],"lack":[50],"transferability":[51],"for":[52,75,92,215,262,322,339,430],"new":[53,303],"products.":[54,166,304],"Inspired":[55,305],"recent":[58,308],"development":[59],"pre-trained":[61,311],"models":[63,313],"(PLMs),":[64,314],"this":[66,83,330],"paper,":[67,331],"we":[68,85,110,131,169,315,332,357,384],"make":[69,316],"attempt":[71,318],"adapt":[73,320],"PLMs":[74,321],"mitigate":[78,325],"above":[80,327],"issues.":[81,328],"To":[82],"end,":[84],"develop":[86,333],"KINDLE,":[87,334],"<b>K</b>nowledge-dr<b>I</b>ven":[89,336],"pre-traini<b>N</b>g":[90,337],"framework":[91,338],"pro<b>D</b>uct":[93,340],"<b>LE</b>arning,":[95,342],"which":[96,130,343],"can":[97,344],"preserve":[98,345],"contextual":[100,347],"semantics":[101,348],"multi-faceted":[103,350],"knowledge":[105,125,135,141,180,185,198,214,352,372,378,395,401,414,429],"<i>robustly</i>":[106,353],"<i>flexibly</i>.":[108,355],"Specifically,":[109,356],"first":[111,358],"extend":[112,359],"tranditional":[113],"one-stage":[114,361],"pre-training":[115,119,362,366],"two-stage":[118,365],"framework,":[120,367],"i.e.,":[121],"acquisition":[123,126,199,415],"stage":[127],"respectively,":[128],"exploit":[132,369],"deliberate":[134,371],"encoder":[136,373],"ensure":[138,375],"smooth":[140,377],"fusion":[142,379],"into":[143,380],"PLM":[144,157],"without":[145],"interfering":[146],"its":[147],"original":[148],"function.":[149],"Then":[150],"hierarchical":[152],"skeleton":[153],"attention":[154],"compatible":[155],"with":[156],"is":[158,206,422],"introduced":[159],"capture":[161,287],"information":[164],"In":[167,290,329,382],"addition,":[168,291,383],"propose":[170,385],"multi-objective":[172,387],"heterogeneous":[173,388],"embedding":[174,389],"method":[175,390],"represent":[177,392],"thousands":[178,393],"elements.":[181,396],"This":[182,397],"helps":[183,398],"KINDLE&#x00A0;calibrate":[184],"noise":[186,402],"sparsity":[188,404],"automatically":[189,209,405],"replacing":[191,407],"isolated":[192,408],"classes":[193,409],"training":[195,411],"targets":[196,412],"tasks.":[200,218,416,433,450],"Furthermore,":[201,417],"an":[202,418],"input-aware":[203,419],"gating":[204,420],"network":[205,421],"proposed":[207,423],"select":[210,425],"most":[212,427],"relevant":[213,428],"different":[216,431],"downstream":[217,233,432,449],"Finally,":[219,434],"extensive":[220,435],"experiments":[221,436],"demonstrated":[223,438],"advantages":[225,440],"KINDLE&#x00A0;over":[227],"state-of-the-art":[229,445],"baselines":[230,446],"across":[231,447],"three":[232,448],"tasks,":[234],"personalized":[237],"classification,":[242],"on":[243],"both":[244],"regular":[245],"zero-shot":[247],"settings.":[248],"provides":[260],"benefits":[261],"variety":[264],"including":[267],"The":[273],"their":[284],"inability":[285],"are":[298],"not":[299],"easily":[300],"transferable":[301],"advance":[309],"traditional":[360],"PLM.":[381],"KINDLE":[399,442],"calibrate":[400],"over":[443]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}