{"id":"https://openalex.org/W7134958932","doi":"https://doi.org/10.1109/icdmw69685.2025.00129","title":"Responsible Imputation of User Behavior Surveys via Mask-Aware Transformers","display_name":"Responsible Imputation of User Behavior Surveys via Mask-Aware Transformers","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134958932","doi":"https://doi.org/10.1109/icdmw69685.2025.00129"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5128755722","display_name":"Aman Shukla","orcid":null},"institutions":[{"id":"https://openalex.org/I75746372","display_name":"ZTE (United States)","ror":"https://ror.org/0518yg160","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098582","https://openalex.org/I75746372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Shukla","raw_affiliation_strings":["Resonate Networks, Inc.,Virginia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Resonate Networks, Inc.,Virginia,USA","institution_ids":["https://openalex.org/I75746372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128798964","display_name":"Rishabh Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I75746372","display_name":"ZTE (United States)","ror":"https://ror.org/0518yg160","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098582","https://openalex.org/I75746372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishabh Kumar","raw_affiliation_strings":["Resonate Networks, Inc.,Virginia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Resonate Networks, Inc.,Virginia,USA","institution_ids":["https://openalex.org/I75746372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056979229","display_name":"Daniel P. Scantlebury","orcid":null},"institutions":[{"id":"https://openalex.org/I75746372","display_name":"ZTE (United States)","ror":"https://ror.org/0518yg160","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098582","https://openalex.org/I75746372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Patrick Scantlebury","raw_affiliation_strings":["Resonate Networks, Inc.,Virginia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Resonate Networks, Inc.,Virginia,USA","institution_ids":["https://openalex.org/I75746372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75746372"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.29030001163482666,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.29030001163482666,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.11680000275373459,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11800","display_name":"User Authentication and Security Systems","score":0.08669999986886978,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/imputation","display_name":"Imputation (statistics)","score":0.6618000268936157},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.35280001163482666},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.32010000944137573},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.24490000307559967},{"id":"https://openalex.org/keywords/intrusion-detection-system","display_name":"Intrusion detection system","score":0.24420000612735748}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.6618000268936157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5859000086784363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4690999984741211},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35280001163482666},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25380000472068787},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.24490000307559967},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.23849999904632568}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1694624362","https://openalex.org/W2064186732","https://openalex.org/W2115098571","https://openalex.org/W2963917042","https://openalex.org/W3035623224","https://openalex.org/W4293055795","https://openalex.org/W4319335604","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"User":[0],"behavior":[1],"data":[2,198],"collected":[3],"through":[4],"surveys":[5],"is":[6,37],"foundational":[7],"to":[8],"applications":[9],"in":[10,33,63,133,196],"AdTech,":[11],"personalization,":[12],"and":[13,29,39,87,130,146,161,167,192,205],"consumer":[14],"intelligence.":[15],"However,":[16],"the":[17,44,90,141],"structured":[18,144],"nature":[19],"of":[20,46,143],"survey":[21,66,71,197],"fielding":[22],"governed":[23],"by":[24],"routing":[25,97],"logic,":[26],"platform":[27],"constraints,":[28],"user":[30,52],"fatigue":[31],"results":[32,171],"pervasive":[34],"missingness":[35],"that":[36,49,107],"non-random":[38],"logic-driven.":[40],"These":[41],"gaps":[42],"hinder":[43],"effectiveness":[45],"downstream":[47],"systems":[48],"rely":[50],"on":[51,111],"representations.":[53],"We":[54,149],"present":[55],"a":[56,152,186,201],"Transformer-based":[57],"framework":[58],"for":[59,179,203],"imputing":[60],"missing":[61],"responses":[62,72],"multi-choice":[64],"behavioral":[65],"data.":[67],"Our":[68,137,183],"model":[69,91,165],"encodes":[70],"as":[73],"flattened":[74],"multi-hot":[75],"vectors":[76],"with":[77],"associated":[78],"binary":[79],"masks":[80],"indicating":[81,177],"fielded":[82],"questions.":[83],"Through":[84],"column-wise":[85],"attention":[86,145],"mask-aware":[88],"supervision,":[89],"learns":[92],"highfidelity":[93],"imputations":[94],"while":[95],"honoring":[96],"logic.":[98],"To":[99],"enforce":[100],"plausibility,":[101],"we":[102,116],"apply":[103],"strict":[104],"logical":[105],"enforcement":[106],"filters":[108],"predictions":[109],"based":[110],"domain-aligned":[112],"consistency":[113],"rules.":[114],"Empirically,":[115],"evaluate":[117],"imputation":[118,154],"performance":[119,174],"under":[120],"synthetic":[121],"masking":[122],"across":[123,158,175],"increasing":[124],"sparsity":[125],"levels,":[126],"demonstrating":[127],"robust":[128],"F1":[129],"recall":[131],"even":[132],"highly":[134],"incomplete":[135],"settings.":[136],"ablation":[138],"studies":[139],"confirm":[140],"importance":[142],"supervision":[147],"masking.":[148],"further":[150],"conduct":[151],"responsible":[153,204],"audit,":[155],"assessing":[156],"fairness":[157],"age,":[159],"gender,":[160],"ethnicity-":[162],"capturing":[163],"both":[164],"fit":[166],"outcome":[168],"parity.":[169],"The":[170],"reveal":[172],"stable":[173],"subgroups,":[176],"suitability":[178],"equitable":[180],"industrial":[181],"deployment.":[182],"approach":[184],"closes":[185],"critical":[187],"gap":[188],"between":[189],"modeling":[190],"sophistication":[191],"real-world":[193],"deployment":[194],"constraints":[195],"pipelines,":[199],"setting":[200],"precedent":[202],"scalable":[206],"imputation.":[207]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-12T00:00:00"}