{"id":"https://openalex.org/W7131893747","doi":"https://doi.org/10.1109/tbdata.2026.3668673","title":"PEXP: A Scalable Parallel Tree-Based Framework for Interpreting Models on Big Data","display_name":"PEXP: A Scalable Parallel Tree-Based Framework for Interpreting Models on Big Data","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7131893747","doi":"https://doi.org/10.1109/tbdata.2026.3668673"},"language":null,"primary_location":{"id":"doi:10.1109/tbdata.2026.3668673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3668673","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-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/A5047519765","display_name":"Wendong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Dong Jiang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0000-7969-6386","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127349341","display_name":"Chih-Yung Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Yung Chang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0672-5593","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004546741","display_name":"Tzu-Chia Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Chia Huang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Tamkang University, New Taipei, Taiwan","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127153282","display_name":"Yu-Ting Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I107470533","display_name":"Tamkang University","ror":"https://ror.org/04tft4718","country_code":"TW","type":"education","lineage":["https://openalex.org/I107470533"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ting Chin","raw_affiliation_strings":["Department of the Aritificial Intelligence, Tamkang University, New Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of the Aritificial Intelligence, Tamkang University, New Taipei, Taiwan","institution_ids":["https://openalex.org/I107470533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011943818","display_name":"Diptendu Sinha Roy","orcid":"https://orcid.org/0000-0001-9731-2534"},"institutions":[{"id":"https://openalex.org/I9523339","display_name":"National Institute of Technology Meghalaya","ror":"https://ror.org/020vd6n84","country_code":"IN","type":"education","lineage":["https://openalex.org/I9523339"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Diptendu Sinha Roy","raw_affiliation_strings":["Department of Computer Science and Engineering, National Institute of Technology, Shillong, India"],"raw_orcid":"https://orcid.org/0000-0001-9731-2534","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Institute of Technology, Shillong, India","institution_ids":["https://openalex.org/I9523339"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22287829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"4","first_page":"1177","last_page":"1194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.42649999260902405,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.42649999260902405,"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/T12031","display_name":"Speech and dialogue systems","score":0.051500000059604645,"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/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.04729999974370003,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8633000254631042},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8022000193595886},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7469000220298767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4684999883174896},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4120999872684479},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.39989998936653137},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772000074386597},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8633000254631042},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8022000193595886},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7469000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5304999947547913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5030999779701233},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2026.3668673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3668673","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6508216650","display_name":"Bullying Detection and Attention Recognition System Based on Deep Learning","funder_award_id":"NSTC112-2622-E032-005","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,9,45,149,174,193,207],"big":[3,179],"data":[4,97,180,208],"has":[5],"fueled":[6],"the":[7,150,154,172,191],"success":[8],"deep":[10],"learning;":[11],"however,":[12],"its":[13,22,128],"inherent":[14],"\u201dblack":[15],"box\u201d":[16],"nature":[17],"poses":[18],"significant":[19,161],"challenges":[20],"for":[21,79,178,212],"adoption":[23],"in":[24,167,189],"safety-critical":[25],"domains.":[26],"Existing":[27],"interpretable":[28,130,165],"machine":[29],"learning":[30],"methods":[31,166],"offer":[32],"partial":[33],"solutions":[34],"but":[35],"often":[36],"struggle":[37],"with":[38],"model":[39,47,133],"fidelity,":[40],"inconsistent":[41],"explanations,":[42,175],"a":[43,88,93,107,146,183,201],"lack":[44],"holistic":[46],"understanding,":[48],"and":[49,81,105,119,138,171,209],"critically,":[50],"computational":[51],"inefficiency,":[52],"especially":[53],"when":[54],"applied":[55],"to":[56,110,144],"models":[57],"trained":[58],"on":[59,153],"large-scale":[60],"datasets.":[61],"To":[62],"overcome":[63],"these":[64,112],"hurdles,":[65],"this":[66],"paper":[67],"introduces":[68],"Parallel":[69,124],"Explainer":[70],"(PEXP),":[71],"an":[72],"innovative":[73],"parallel":[74],"tree-based":[75],"interpretation":[76],"framework":[77],"designed":[78],"scalability":[80],"comprehensive":[82],"understanding.":[83],"PEXP":[84,121],"initiates":[85],"by":[86,204],"generating":[87],"localized":[89],"sample":[90],"set":[91],"around":[92],"target":[94],"instance":[95],"through":[96],"distribution-aware":[98],"perturbations.":[99],"It":[100],"then":[101],"computes":[102],"similarity":[103],"scores":[104],"employs":[106],"kernel":[108],"function":[109],"weight":[111],"samples":[113,143],"effectively.":[114],"Leveraging":[115],"concepts":[116],"from":[117],"Bagging":[118],"Boosting,":[120],"efficiently":[122],"constructs":[123],"Ensemble":[125],"Trees":[126],"as":[127],"core":[129],"model.":[131],"This":[132],"provides":[134],"feature":[135],"importance-based":[136],"explanations":[137],"aggregates":[139],"insights":[140,211],"across":[141],"all":[142],"achieve":[145],"global":[147],"understanding":[148],"model's":[151],"behavior":[152],"entire":[155],"dataset.":[156],"Experimental":[157],"results":[158],"demonstrate":[159],"PEXP's":[160,187],"advantages":[162],"over":[163],"mainstream":[164],"both":[168],"runtime":[169],"efficiency":[170],"quality":[173],"particularly":[176],"crucial":[177],"analytics.":[181],"Furthermore,":[182],"case":[184],"study":[185],"illustrates":[186],"application":[188],"enhancing":[190],"interpretability":[192],"video":[194],"anomaly":[195],"detection":[196],"systems":[197],"within":[198],"smart":[199],"cities,":[200],"domain":[202],"characterized":[203],"large":[205],"volumes":[206],"offers":[210],"improving":[213],"Transformer-based":[214],"architectures.":[215]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-02-28T00:00:00"}