{"id":"https://openalex.org/W2595017202","doi":"https://doi.org/10.24963/ijcai.2017/371","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","display_name":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2595017202","doi":"https://doi.org/10.24963/ijcai.2017/371","mag":"2595017202"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/371","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/371","pdf_url":"https://www.ijcai.org/proceedings/2017/0371.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0371.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024337758","display_name":"Andrew Slavin Ross","orcid":"https://orcid.org/0000-0002-2368-6979"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Slavin Ross","raw_affiliation_strings":["Harvard University","Harvard University, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, United States","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058890009","display_name":"Michael C. Hughes","orcid":"https://orcid.org/0000-0003-4859-7400"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C. Hughes","raw_affiliation_strings":["Harvard University","Harvard University, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, United States","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Finale Doshi-Velez","raw_affiliation_strings":["Harvard University","Harvard University, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, United States","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024337758"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":6.028,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96874577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2662","last_page":"2670"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9979000091552734,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.6779888868331909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6024282574653625},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5956770181655884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5740272998809814},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5163280367851257},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5066395401954651},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5005502700805664},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4755135178565979},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42145949602127075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20091283321380615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779888868331909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6024282574653625},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5956770181655884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5740272998809814},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5163280367851257},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5066395401954651},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5005502700805664},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4755135178565979},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42145949602127075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20091283321380615},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2017/371","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/371","pdf_url":"https://www.ijcai.org/proceedings/2017/0371.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.03717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.03717","pdf_url":"https://arxiv.org/pdf/1703.03717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2595017202","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1703.03717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1703.03717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.03717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/371","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/371","pdf_url":"https://www.ijcai.org/proceedings/2017/0371.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1072749480","display_name":null,"funder_award_id":"FA9550-17","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G260750634","display_name":null,"funder_award_id":"FA9550-17-1","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3392305090","display_name":null,"funder_award_id":"-16-1-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6029603737","display_name":null,"funder_award_id":"W911NF-16-1-0561","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2595017202.pdf","grobid_xml":"https://content.openalex.org/works/W2595017202.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1601924930","https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1996796871","https://openalex.org/W2047956997","https://openalex.org/W2100960835","https://openalex.org/W2112594540","https://openalex.org/W2119858020","https://openalex.org/W2153332911","https://openalex.org/W2195388612","https://openalex.org/W2279943773","https://openalex.org/W2282821441","https://openalex.org/W2346578521","https://openalex.org/W2399450173","https://openalex.org/W2439568532","https://openalex.org/W2440159969","https://openalex.org/W2540757487","https://openalex.org/W2549418531","https://openalex.org/W2549603914","https://openalex.org/W2552204443","https://openalex.org/W2553389628","https://openalex.org/W2556172574","https://openalex.org/W2562979205","https://openalex.org/W2567533607","https://openalex.org/W2594475271","https://openalex.org/W2952688545","https://openalex.org/W2962851944","https://openalex.org/W2964082701","https://openalex.org/W3101609372","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2295107390","https://openalex.org/W2282821441","https://openalex.org/W1849277567","https://openalex.org/W2194775991","https://openalex.org/W2605409611","https://openalex.org/W3101609372","https://openalex.org/W2594475271","https://openalex.org/W2963996492","https://openalex.org/W2945976633","https://openalex.org/W2594633041","https://openalex.org/W2521737809","https://openalex.org/W2332488709","https://openalex.org/W2112796928","https://openalex.org/W2108598243","https://openalex.org/W1915485278","https://openalex.org/W3206275068","https://openalex.org/W2965812174","https://openalex.org/W2997592403"],"abstract_inverted_index":{"Expressive":[0],"classifiers":[1],"such":[2],"as":[3,97,99],"neural":[4],"networks":[5],"are":[6,103],"among":[7],"the":[8,36,43,46,52,59],"most":[9],"accurate":[10],"supervised":[11],"learning":[12],"methods":[13,81],"in":[14,27,124],"use":[15],"today,":[16],"but":[17,84],"their":[18],"opaque":[19],"decision":[20,60,95,100],"boundaries":[21,96,101],"make":[22],"them":[23],"difficult":[24],"to":[25,34,51,58,89],"trust":[26],"critical":[28],"applications.":[29],"We":[30],"propose":[31],"a":[32,56],"method":[33],"explain":[35],"predictions":[37],"of":[38,45,68,75],"any":[39],"differentiable":[40],"model":[41],"via":[42],"gradient":[44],"class":[47],"label":[48],"with":[49,105],"respect":[50],"input":[53,73],"(which":[54],"provides":[55],"normal":[57],"boundary).":[61],"Not":[62],"only":[63],"is":[64],"this":[65],"approach":[66,114],"orders":[67],"magnitude":[69],"faster":[70],"at":[71],"identifying":[72],"dimensions":[74],"high":[76],"sensitivity":[77],"than":[78],"sample-based":[79],"perturbation":[80],"(e.g.":[82],"LIME),":[83],"it":[85],"also":[86],"lends":[87],"itself":[88],"efficiently":[90],"discovering":[91],"multiple":[92,109],"qualitatively":[93],"different":[94],"well":[98],"that":[102],"consistent":[104],"expert":[106],"annotation.":[107],"On":[108],"datasets,":[110],"we":[111],"show":[112],"our":[113],"generalizes":[115],"much":[116],"better":[117],"when":[118],"test":[119],"conditions":[120],"differ":[121],"from":[122],"those":[123],"training.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}