{"id":"https://openalex.org/W4385568269","doi":"https://doi.org/10.1145/3580305.3599544","title":"Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers","display_name":"Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568269","doi":"https://doi.org/10.1145/3580305.3599544"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599544","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5003837744","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-0540-6758"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025877787","display_name":"Bowen Jin","orcid":"https://orcid.org/0000-0003-1295-2829"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Jin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049591203","display_name":"Xiusi Chen","orcid":"https://orcid.org/0000-0002-9713-8000"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiusi Chen","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070702509","display_name":"Yanzhen Shen","orcid":"https://orcid.org/0009-0005-0113-3942"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhen Shen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062324293","display_name":"Yunyi Zhang","orcid":"https://orcid.org/0000-0001-9790-4855"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyi Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"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/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Meng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5003837744"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.3826,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84828527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3458","last_page":"3469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983999729156494,"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":0.8028019070625305},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6298233270645142},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.596670925617218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564786791801453},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.546916127204895},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5218868851661682},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.49502795934677124},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.49076756834983826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4704935550689697},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4589499235153198},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4518316984176636},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4312950372695923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33511748909950256},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22060537338256836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028019070625305},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6298233270645142},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.596670925617218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564786791801453},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.546916127204895},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5218868851661682},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.49502795934677124},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.49076756834983826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4704935550689697},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4589499235153198},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4518316984176636},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4312950372695923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33511748909950256},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22060537338256836},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599544","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2063335192","display_name":null,"funder_award_id":"2019897","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2104517209","display_name":null,"funder_award_id":"IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3269309973","display_name":null,"funder_award_id":"2118329","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3748775989","display_name":null,"funder_award_id":"HR001121C0165","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6445402324","display_name":null,"funder_award_id":"IIS-19-56151","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6904642173","display_name":null,"funder_award_id":"INCAS Program No. HR001121C0165","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7091742882","display_name":null,"funder_award_id":"HR001121C0165","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W103340358","https://openalex.org/W746911252","https://openalex.org/W2089941494","https://openalex.org/W2109480754","https://openalex.org/W2142955026","https://openalex.org/W2149151184","https://openalex.org/W2285986798","https://openalex.org/W2362855512","https://openalex.org/W2428528690","https://openalex.org/W2533513334","https://openalex.org/W2743104969","https://openalex.org/W2788125153","https://openalex.org/W2801930304","https://openalex.org/W2889577585","https://openalex.org/W2890931111","https://openalex.org/W2920882081","https://openalex.org/W2952205826","https://openalex.org/W2963413667","https://openalex.org/W2963464979","https://openalex.org/W2963804400","https://openalex.org/W2965857891","https://openalex.org/W2979576300","https://openalex.org/W3002924435","https://openalex.org/W3012871709","https://openalex.org/W3015453090","https://openalex.org/W3034999214","https://openalex.org/W3035324702","https://openalex.org/W3088624469","https://openalex.org/W3101606352","https://openalex.org/W3114232366","https://openalex.org/W3166913490","https://openalex.org/W3171416056","https://openalex.org/W3213175220","https://openalex.org/W3214566704","https://openalex.org/W4290875442"],"related_works":["https://openalex.org/W2044507188","https://openalex.org/W2556319748","https://openalex.org/W3162567751","https://openalex.org/W4285260836","https://openalex.org/W4221088574","https://openalex.org/W4282018961","https://openalex.org/W3094076422","https://openalex.org/W4312365371","https://openalex.org/W3046775127","https://openalex.org/W4220686584"],"abstract_inverted_index":{"Instead":[0],"of":[1,87,112,167],"relying":[2],"on":[3,31,172,185],"human-annotated":[4],"training":[5,197],"samples":[6],"to":[7,17,76,142,162,194],"build":[8],"a":[9,63,93,129,156],"classifier,":[10],"weakly":[11,32],"supervised":[12,33,189],"scientific":[13,145],"paper":[14,34,79,91],"classification":[15,35],"aims":[16],"classify":[18,143],"papers":[19,108,146],"only":[20,49],"using":[21],"category":[22,25],"descriptions":[23],"(e.g.,":[24],"names,":[26],"category-indicative":[27],"keywords).":[28],"Existing":[29],"studies":[30],"are":[36,160],"less":[37],"concerned":[38],"with":[39,187],"two":[40,165,173],"challenges:":[41],"(1)":[42],"Papers":[43],"should":[44,73,98],"be":[45,74],"classified":[46],"into":[47,59],"not":[48],"coarse-grained":[50],"research":[51],"topics":[52],"but":[53],"also":[54],"fine-grained":[55,66],"themes,":[56,61],"and":[57,65,69,81,109,114,137,155,183],"potentially":[58],"multiple":[60],"given":[62],"large":[64],"label":[67],"space;":[68],"(2)":[70],"full":[71],"text":[72],"utilized":[75],"complement":[77],"the":[78,89,100,110,133,138,164],"title":[80],"abstract":[82],"for":[83],"classification.":[84],"Moreover,":[85],"instead":[86],"viewing":[88],"entire":[90],"as":[92,104],"long":[94],"linear":[95],"sequence,":[96],"one":[97],"exploit":[99],"structural":[101,168],"information":[102],"such":[103],"citation":[105],"links":[106],"across":[107],"hierarchy":[111,140],"sections":[113],"paragraphs":[115],"in":[116,123],"each":[117],"paper.":[118],"To":[119],"tackle":[120],"these":[121],"challenges,":[122],"this":[124],"study,":[125],"we":[126],"propose":[127],"FUTEX,":[128],"framework":[130],"that":[131,177,191],"uses":[132],"cross-paper":[134],"network":[135],"structure":[136,141],"in-paper":[139],"full-text":[144],"under":[147],"weak":[148],"supervision.":[149],"A":[150],"network-aware":[151],"contrastive":[152],"fine-tuning":[153],"module":[154,159],"hierarchy-aware":[157],"aggregation":[158],"designed":[161],"leverage":[163],"types":[166],"signals,":[169],"respectively.":[170],"Experiments":[171],"benchmark":[174],"datasets":[175],"demonstrate":[176],"FUTEX":[178],"significantly":[179],"outperforms":[180],"competitive":[181],"baselines":[182],"is":[184],"par":[186],"fully":[188],"classifiers":[190],"use":[192],"1,000":[193],"60,000":[195],"ground-truth":[196],"samples.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}