{"id":"https://openalex.org/W4399605312","doi":"https://doi.org/10.1145/3630744.3658614","title":"Advancing Web Science through Foundation Model for Tabular Data","display_name":"Advancing Web Science through Foundation Model for Tabular Data","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4399605312","doi":"https://doi.org/10.1145/3630744.3658614"},"language":"en","primary_location":{"id":"doi:10.1145/3630744.3658614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3658614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3658614","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM Web Science Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3658614","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047376300","display_name":"Inwon Kang","orcid":"https://orcid.org/0000-0001-8912-287X"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Inwon Kang","raw_affiliation_strings":["Computer Science, Rensselaer Polytechnic Institute, United States"],"raw_orcid":"https://orcid.org/0000-0001-8912-287X","affiliations":[{"raw_affiliation_string":"Computer Science, Rensselaer Polytechnic Institute, United States","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047376300"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.6605,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66211026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"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":0.9836999773979187,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9740999937057495,"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":0.7911874055862427},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5894225835800171},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5404651165008545},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47557082772254944},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42893850803375244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28330713510513306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911874055862427},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5894225835800171},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5404651165008545},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47557082772254944},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42893850803375244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28330713510513306},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630744.3658614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3658614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3658614","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM Web Science Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3630744.3658614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3658614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3658614","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM Web Science Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399605312.pdf","grobid_xml":"https://content.openalex.org/works/W4399605312.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2084701050","https://openalex.org/W2116341502","https://openalex.org/W2527672088","https://openalex.org/W2542459869","https://openalex.org/W2786532017","https://openalex.org/W2999529051","https://openalex.org/W3049565363","https://openalex.org/W3102272852","https://openalex.org/W3159500102","https://openalex.org/W3205014346","https://openalex.org/W3216660278","https://openalex.org/W4224308799","https://openalex.org/W4381803868","https://openalex.org/W4392737178","https://openalex.org/W4394671193","https://openalex.org/W6888864499","https://openalex.org/W6944988488"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"the":[1,8,13,210,217],"landscape":[2],"of":[3,44,213],"web":[4,124,189,218],"science":[5,125,190],"expands,":[6],"handling":[7,70,209],"vast":[9],"datasets":[10,34],"collected":[11],"from":[12,216],"Web":[14],"while":[15,219],"preserving":[16,220],"computational":[17,193],"efficiency":[18],"and":[19,57,89,110,130,134,146,191,197],"privacy":[20,111,195],"remains":[21],"a":[22,28,36,66,82,114,120,175,205],"significant":[23],"challenge.":[24],"Data":[25],"distillation":[26,52],"offers":[27],"compelling":[29],"solution":[30,68],"by":[31],"condensing":[32],"large":[33,71,211],"into":[35],"distilled":[37,171],"subset":[38],"that":[39,55],"retains":[40],"essential":[41],"characteristics.":[42],"Part":[43],"my":[45,76],"ongoing":[46],"thesis":[47],"work":[48],"on":[49],"tabular":[50,63,96,179],"data":[51,101,105,129,180,214],"has":[53],"shown":[54],"autoencoders":[56],"clustering":[58],"algorithms":[59],"can":[60,93],"effectively":[61],"distill":[62,94],"datasets,":[64,97,165],"offering":[65],"promising":[67],"for":[69,123,159,178,204,208],"datasets.":[72],"Building":[73],"upon":[74],"this,":[75],"next":[77],"step":[78],"is":[79],"to":[80,87,143,150,184],"develop":[81],"versatile":[83,121,206],"pre-trained":[84],"model":[85,92,116,138,177],"analogous":[86],"BERT":[88],"RoBERTa.":[90],"This":[91,137],"arbitrary":[95],"streamlining":[98],"processes":[99],"like":[100],"size":[102],"reduction,":[103],"synthetic":[104,164],"generation,":[106],"large-scale":[107],"analysis,":[108,161],"reproducibility,":[109],"preservation.":[112],"Such":[113],"foundation":[115,176],"will":[117,139,147],"serve":[118],"as":[119,155],"tool":[122,207],"research,":[126],"making":[127],"both":[128],"research":[131],"more":[132],"accessible":[133],"computationally":[135],"efficient.":[136],"not":[140],"be":[141,148],"limited":[142],"downstream":[144],"classification":[145],"applicable":[149],"many":[151],"further":[152],"uses,":[153],"such":[154],"reducing":[156],"dataset":[157],"sizes":[158],"efficient":[160],"producing":[162],"privatized":[163],"or":[166],"enhancing":[167],"reproducibility":[168],"through":[169],"shared":[170],"data.":[172],"By":[173],"developing":[174],"distillation,":[181],"I":[182],"aim":[183],"unlock":[185],"new":[186],"avenues":[187],"in":[188],"improve":[192],"accessibility,":[194],"protection,":[196],"reproducibility.":[198],"The":[199],"proposed":[200],"direction":[201],"holds":[202],"promise":[203],"amounts":[212],"generated":[215],"its":[221],"essence.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}