{"id":"https://openalex.org/W4306316989","doi":"https://doi.org/10.1145/3511808.3557522","title":"Utilizing Contrastive Learning To Address Long Tail Issue in Product Categorization","display_name":"Utilizing Contrastive Learning To Address Long Tail Issue in Product Categorization","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306316989","doi":"https://doi.org/10.1145/3511808.3557522"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557522","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-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/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210144225","display_name":"Rakuten (United States)","ror":"https://ror.org/04bsz5816","country_code":"US","type":"company","lineage":["https://openalex.org/I1301041018","https://openalex.org/I4210144225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, USA","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I4210144225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100734914","display_name":"Tianqi Wang","orcid":"https://orcid.org/0000-0002-6573-4123"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianqi Wang","raw_affiliation_strings":["University of Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100333516"],"corresponding_institution_ids":["https://openalex.org/I4210144225","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42054514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5081","last_page":"5082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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":0.9972000122070312,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9922999739646912,"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/categorization","display_name":"Categorization","score":0.768444299697876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633110046386719},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4988131523132324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319782257080078},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42998558282852173},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32975733280181885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08809179067611694}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.768444299697876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633110046386719},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4988131523132324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319782257080078},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42998558282852173},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32975733280181885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08809179067611694},{"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:10.1145/3511808.3557522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557522","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2148143831","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2985757090","https://openalex.org/W3034601242","https://openalex.org/W3094609756","https://openalex.org/W3128046581","https://openalex.org/W4297683907"],"related_works":["https://openalex.org/W2365213443","https://openalex.org/W3013319096","https://openalex.org/W2325924483","https://openalex.org/W2151447942","https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W3107474891","https://openalex.org/W1552159754","https://openalex.org/W1770916124"],"abstract_inverted_index":{"Neural":[0],"network":[1],"models":[2,51],"trained":[3],"in":[4,53,98,166],"a":[5,99,107,131,164],"supervised":[6],"learning":[7,63,120,177],"way":[8],"have":[9],"become":[10],"dominant.":[11],"Although":[12],"high":[13],"performances":[14],"can":[15,31],"be":[16,32,143],"achieved":[17],"when":[18],"training":[19,29,130],"data":[20,40,135],"is":[21,41],"ample,":[22],"the":[23,66,83,114,123,150,155,167,175],"performance":[24,35,184],"on":[25,73,76,82,133,154],"labels":[26],"with":[27],"sparse":[28],"instances":[30,172],"poor.":[33],"This":[34],"drift":[36],"caused":[37],"by":[38,186],"imbalanced":[39],"named":[42],"as":[43],"long":[44],"tail":[45],"issue":[46],"and":[47,128],"impacts":[48],"many":[49],"NN":[50],"used":[52],"reality.":[54],"In":[55,103,160],"this":[56],"talk,":[57],"we":[58,70,105,147,162],"will":[59,71],"firstly":[60],"review":[61],"machine":[62],"approaches":[64],"addressing":[65],"long-tail":[67],"issue.":[68],"Next,":[69],"report":[72],"our":[74,144],"effort":[75],"applying":[77],"one":[78],"recent":[79],"LT-addressing":[80],"method":[81,152],"item":[84],"categorization":[85],"(IC)":[86],"task":[87,117],"that":[88,149],"aims":[89],"to":[90,142],"classify":[91],"product":[92],"description":[93],"texts":[94],"into":[95,118,137],"leaf":[96],"nodes":[97],"category":[100],"taxonomy":[101],"tree.":[102],"particular,":[104],"adopted":[106],"new":[108],"method,":[109],"which":[110],"consists":[111],"of":[112],"decoupling":[113],"entire":[115],"classification":[116,158],"(a)":[119],"representations":[121],"using":[122],"K-positive":[124],"contrastive":[125],"loss":[126],"(KCL)":[127],"(b)":[129],"classifier":[132],"balanced":[134],"set,":[136],"IC":[138,156,183],"tasks.":[139],"Using":[140],"SimCSE":[141],"self-learning":[145],"backbone,":[146],"demonstrated":[148],"proposed":[151],"works":[153],"text":[157],"task.":[159],"addition,":[161],"spotted":[163],"shortcoming":[165],"KCL:":[168],"false":[169],"negative":[170],"(FN)":[171],"may":[173],"harm":[174],"representation":[176],"step.":[178],"After":[179],"eliminating":[180],"FN":[181],"instances,":[182],"(measured":[185],"macro-F1)":[187],"has":[188],"been":[189],"further":[190],"improved.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}