{"id":"https://openalex.org/W4229069923","doi":"https://doi.org/10.1145/3477314.3507232","title":"Similarity-based uncertainty scores for interpretable deep learning in scientific applications","display_name":"Similarity-based uncertainty scores for interpretable deep learning in scientific applications","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229069923","doi":"https://doi.org/10.1145/3477314.3507232"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507232","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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/A5042888174","display_name":"Lilly Roelofs","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lilly Roelofs","raw_affiliation_strings":["University of Houston"],"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075292273","display_name":"Claire Weissman","orcid":null},"institutions":[{"id":"https://openalex.org/I138943879","display_name":"Whitman College","ror":"https://ror.org/05axv8155","country_code":"US","type":"education","lineage":["https://openalex.org/I138943879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Weissman","raw_affiliation_strings":["Whitman College"],"affiliations":[{"raw_affiliation_string":"Whitman College","institution_ids":["https://openalex.org/I138943879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005267835","display_name":"Daniela Raicu","orcid":"https://orcid.org/0000-0002-2165-7234"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Raicu","raw_affiliation_strings":["DePaul University"],"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001027068","display_name":"Jacob Furst","orcid":null},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Furst","raw_affiliation_strings":["DePaul University"],"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080703148","display_name":"Roselyne Tchoua","orcid":"https://orcid.org/0000-0002-7195-4456"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roselyne Tchoua","raw_affiliation_strings":["DePaul University"],"affiliations":[{"raw_affiliation_string":"DePaul University","institution_ids":["https://openalex.org/I118353179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042888174"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03065072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1152","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991000294685364,"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":0.9991000294685364,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9986000061035156,"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":0.9980999827384949,"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":0.8649473786354065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7607409358024597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6651121377944946},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6283987164497375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6076913475990295},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5875976085662842},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5815335512161255},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5627170205116272},{"id":"https://openalex.org/keywords/silhouette","display_name":"Silhouette","score":0.5238366723060608},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4974513351917267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4880563020706177},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4763393998146057},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4432005286216736},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3363800346851349}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8649473786354065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607409358024597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6651121377944946},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6283987164497375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6076913475990295},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5875976085662842},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5815335512161255},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5627170205116272},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.5238366723060608},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4974513351917267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4880563020706177},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4763393998146057},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4432005286216736},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3363800346851349},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507232","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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":10,"referenced_works":["https://openalex.org/W1853932049","https://openalex.org/W2047755713","https://openalex.org/W2098777834","https://openalex.org/W2119158865","https://openalex.org/W2187089797","https://openalex.org/W2607662938","https://openalex.org/W2802087177","https://openalex.org/W2904530326","https://openalex.org/W2976823419","https://openalex.org/W3012863385"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W1622964048","https://openalex.org/W30315714","https://openalex.org/W1965274140","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388685194","https://openalex.org/W4310922872"],"abstract_inverted_index":{"There":[0],"is":[1,72],"a":[2,43,81,88,99,111,124,165],"significant":[3],"effort":[4],"to":[5,31,59,66,132,146],"increase":[6],"the":[7,120,149,179,201],"adoption":[8],"of":[9,90,173,190,205],"Deep":[10],"Neural":[11,114],"Networks":[12],"(DNNs)":[13],"in":[14,27,152,209],"fields":[15],"such":[16,75],"as":[17,123],"criminal":[18],"justice":[19],"and":[20,68,106,138,203],"medicine.":[21],"Yet,":[22],"DNNs":[23],"commonly":[24],"fall":[25],"short":[26],"these":[28],"applications":[29],"due":[30],"their":[32],"\"black":[33],"box\"":[34],"nature.":[35],"DNN":[36],"research":[37],"often":[38],"focuses":[39],"more":[40],"on":[41,104,171],"achieving":[42],"higher":[44],"classification":[45],"accuracy":[46],"than":[47,118],"traditional":[48],"Machine":[49],"Learning":[50],"(ML)":[51],"algorithms,":[52],"but":[53,83],"this":[54,95],"does":[55],"not":[56,78],"apply":[57],"well":[58],"data":[60,107,198],"sets":[61],"that":[62,178],"are":[63],"inherently":[64],"difficult":[65],"label":[67],"classify,":[69],"hence":[70],"interpretability":[71],"crucial.":[73],"In":[74,94],"cases,":[76],"scientists":[77],"only":[79],"expect":[80],"prediction":[82],"also":[84],"an":[85,135,155],"explanation":[86],"and/or":[87],"measure":[89],"confidence":[91],"per":[92,185],"prediction.":[93,141],"work,":[96],"we":[97,129],"propose":[98],"novel":[100],"uncertainty":[101,136,143,162,207],"metric":[102,126,208],"based":[103],"clustering":[105],"similarity":[108],"learned":[109],"through":[110],"Siamese":[112],"Convolutional":[113],"Network":[115],"(SCNN).":[116],"Rather":[117],"using":[119,164],"silhouette":[121],"coefficient":[122],"quality":[125],"for":[127,195],"clustering,":[128],"use":[130],"it":[131],"independently":[133],"provide":[134],"score":[137],"supplement":[139],"each":[140],"These":[142],"scores":[144,163],"serve":[145],"better":[147],"inform":[148],"end-user's":[150],"decision,":[151],"our":[153,161,186,206],"case":[154],"application":[156],"domain":[157],"expert.":[158],"We":[159,176],"evaluate":[160],"K-Nearest":[166],"Neighbors":[167],"(KNN)":[168],"classifier":[169],"built":[170],"top":[172,180],"SCNN":[174],"features.":[175],"show":[177],"15%":[181],"most":[182],"uncertain":[183],"points---flagged":[184],"metric---capture":[187],"over":[188],"50%":[189],"KNN":[191],"errors":[192],"(misclassified":[193],"cases)":[194],"three":[196],"different":[197],"sets,":[199],"exhibiting":[200],"versatility":[202],"functionality":[204],"detecting":[210],"difficult-to-classify":[211],"samples.":[212]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}