{"id":"https://openalex.org/W7138289151","doi":"https://doi.org/10.48550/arxiv.2603.15481","title":"TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins","display_name":"TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138289151","doi":"https://doi.org/10.48550/arxiv.2603.15481"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15481","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.15481","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042774172","display_name":"Shovon Niverd Pereira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pereira, Shovon Niverd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643890","display_name":"Krishna Khadka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khadka, Krishna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129675538","display_name":"Yu Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6747999787330627,"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":0.6747999787330627,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.17589999735355377,"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/T10237","display_name":"Cryptography and Data Security","score":0.016100000590085983,"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/feature","display_name":"Feature (linguistics)","score":0.7286999821662903},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6729000210762024},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6197999715805054},{"id":"https://openalex.org/keywords/operationalization","display_name":"Operationalization","score":0.5210999846458435},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5192999839782715},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443000078201294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7286999821662903},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6197999715805054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5192999839782715},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15481","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.15481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15481","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5691226124763489}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data-free":[0],"knowledge":[1],"distillation":[2,116],"enables":[3],"model":[4,133],"compression":[5],"without":[6],"original":[7],"training":[8],"data,":[9],"critical":[10],"for":[11,54,131],"privacy-sensitive":[12],"tabular":[13,23,36,56,132],"domains.":[14],"However,":[15],"existing":[16],"methods":[17],"does":[18],"not":[19,28],"perform":[20],"well":[21],"on":[22],"data":[24],"because":[25],"they":[26],"do":[27],"explicitly":[29],"address":[30],"feature":[31,48,68],"interactions,":[32],"the":[33],"fundamental":[34],"way":[35],"models":[37],"encode":[38],"predictive":[39],"knowledge.":[40],"We":[41,107],"identify":[42],"interaction":[43,82,111],"diversity,":[44],"systematic":[45],"coverage":[46,112],"of":[47,100],"combinations,":[49],"as":[50,127],"an":[51],"essential":[52],"requirement":[53],"effective":[55],"distillation.":[57],"To":[58],"operationalize":[59],"this":[60],"insight,":[61],"we":[62],"propose":[63],"TabKD,":[64],"which":[65],"learns":[66],"adaptive":[67],"bins":[69],"aligned":[70],"with":[71,115],"teacher":[72,90],"decision":[73],"boundaries,":[74],"then":[75],"generates":[76],"synthetic":[77],"queries":[78],"that":[79,110],"maximize":[80],"pairwise":[81],"coverage.":[83],"Across":[84],"4":[85,89],"benchmark":[86],"datasets":[87],"and":[88],"architectures,":[91],"TabKD":[92],"achieves":[93],"highest":[94],"student-teacher":[95],"agreement":[96],"in":[97],"14":[98],"out":[99],"16":[101],"configurations,":[102],"outperforming":[103],"5":[104],"state-of-the-art":[105],"baselines.":[106],"further":[108],"show":[109],"strongly":[113],"correlates":[114],"quality,":[117],"validating":[118],"our":[119],"core":[120],"hypothesis.":[121],"Our":[122],"work":[123],"establishes":[124],"interaction-focused":[125],"exploration":[126],"a":[128],"principled":[129],"framework":[130],"extraction.":[134]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}