{"id":"https://openalex.org/W3139528458","doi":"https://doi.org/10.1109/bigdata50022.2020.9378081","title":"Interpreting and Evaluating Black Box Models in a Customizable Way","display_name":"Interpreting and Evaluating Black Box Models in a Customizable Way","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3139528458","doi":"https://doi.org/10.1109/bigdata50022.2020.9378081","mag":"3139528458"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/A5100373580","display_name":"Lixin Fan","orcid":"https://orcid.org/0000-0002-8162-7096"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lixin Fan","raw_affiliation_strings":["WeBank AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"WeBank AI, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353167","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-7832-4935"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053105889","display_name":"Yuhao Zhou","orcid":"https://orcid.org/0000-0001-8074-6416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Zhou","raw_affiliation_strings":["WeBank AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"WeBank AI, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425871","display_name":"Tianyu Zhang","orcid":"https://orcid.org/0000-0003-4281-7417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["WeBank AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"WeBank AI, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019677967","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0002-6788-8775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["WeBank AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"WeBank AI, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100373580"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.2177293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"5435","last_page":"5440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9692000150680542,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9620000123977661,"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/interpretability","display_name":"Interpretability","score":0.9459186792373657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822820782661438},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7773780822753906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7515634298324585},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6411489844322205},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6293809413909912},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.6179810166358948},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5505282878875732},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5225690603256226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47700145840644836},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41460347175598145}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9459186792373657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822820782661438},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7773780822753906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7515634298324585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6411489844322205},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6293809413909912},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.6179810166358948},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5505282878875732},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5225690603256226},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47700145840644836},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41460347175598145},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W273955616","https://openalex.org/W1562353621","https://openalex.org/W1678356000","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W2048231652","https://openalex.org/W2107160712","https://openalex.org/W2163605009","https://openalex.org/W2282821441","https://openalex.org/W2371638596","https://openalex.org/W2487898712","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2809925683","https://openalex.org/W2883424428","https://openalex.org/W2891503716","https://openalex.org/W2895144199","https://openalex.org/W2948056727","https://openalex.org/W2962851944","https://openalex.org/W2963749936","https://openalex.org/W2964303497","https://openalex.org/W2981731882","https://openalex.org/W2988437828","https://openalex.org/W3128452405","https://openalex.org/W3148595793","https://openalex.org/W4402843978","https://openalex.org/W6610017368","https://openalex.org/W6623737539","https://openalex.org/W6639204139","https://openalex.org/W6675969807","https://openalex.org/W6684191040","https://openalex.org/W6685133223","https://openalex.org/W6734194636","https://openalex.org/W6736518430"],"related_works":["https://openalex.org/W3036048022","https://openalex.org/W4309224979","https://openalex.org/W3026879719","https://openalex.org/W2797441709","https://openalex.org/W2943982549","https://openalex.org/W2886918272","https://openalex.org/W4387589990","https://openalex.org/W4297660007","https://openalex.org/W4226493464","https://openalex.org/W4312417841"],"abstract_inverted_index":{"A":[0],"vast":[1],"majority":[2],"of":[3,48,83,87,99,114,118,155],"complex":[4],"deep":[5,49],"learning":[6,50],"models":[7,51],"currently":[8],"remain":[9],"black":[10],"boxes,":[11],"which":[12,79],"means":[13],"that":[14,122],"their":[15],"internal":[16],"working":[17],"process":[18],"and":[19,27,38,65,91,143,147,153],"the":[20,24,28,46,56,89,100,112,119,123,129,133,151,156],"logical":[21],"relationships":[22],"between":[23],"input":[25],"data":[26],"output":[29],"predictions":[30],"are":[31],"hidden":[32],"to":[33,94],"human":[34],"users.":[35],"For":[36],"financial":[37],"medical":[39],"use":[40],"cases,":[41],"this":[42,69],"characteristic":[43],"greatly":[44],"hinders":[45],"application":[47],"because":[52],"people":[53],"cannot":[54],"know":[55,126],"logic":[57],"behind":[58],"model":[59,130],"decisions":[60],"such":[61],"as":[62],"stock":[63],"forecast":[64],"disease":[66],"diagnosis.":[67],"In":[68],"paper,":[70],"we":[71],"propose":[72],"CMIE,":[73],"namely,":[74],"Customizable":[75],"Model":[76],"Interpretation":[77],"Evaluation,":[78],"is":[80],"a":[81,136],"set":[82],"customizable":[84],"evaluation":[85,98,109],"methods":[86],"using":[88],"in-model":[90],"post-model":[92],"information":[93],"generate":[95],"multi-dimensional":[96],"interpretability":[97,116],"convolutional":[101],"neural":[102],"networks":[103],"(CNNs)":[104],"with":[105,145],"different":[106],"structures.":[107],"The":[108],"report":[110],"includes":[111],"results":[113],"several":[115],"criteria":[117],"CNNs":[120],"so":[121],"user":[124],"can":[125],"how":[127],"well":[128],"learns":[131],"from":[132],"features":[134],"in":[135],"comprehensible":[137],"way.":[138],"Experiments":[139],"on":[140],"LeNet,":[141],"AlexNet":[142],"VGG-16":[144],"MNIST":[146],"CIFAR-10":[148],"have":[149],"demonstrated":[150],"practicality":[152],"effectiveness":[154],"adopted":[157],"Explainable":[158],"Artificial":[159],"Intelligence":[160],"(XAI)":[161],"method.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}