{"id":"https://openalex.org/W4361806472","doi":"https://doi.org/10.48550/arxiv.2303.16390","title":"Are Data-driven Explanations Robust against Out-of-distribution Data?","display_name":"Are Data-driven Explanations Robust against Out-of-distribution Data?","publication_year":2023,"publication_date":"2023-03-29","ids":{"openalex":"https://openalex.org/W4361806472","doi":"https://doi.org/10.48550/arxiv.2303.16390"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2303.16390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.16390","pdf_url":"https://arxiv.org/pdf/2303.16390","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.16390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100329338","display_name":"Tang Li","orcid":"https://orcid.org/0000-0003-0123-1364"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078959616","display_name":"Fengchun Qiao","orcid":"https://orcid.org/0000-0003-2714-2036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Fengchun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102261650","display_name":"Mengmeng Ma","orcid":"https://orcid.org/0000-0002-2804-2718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Mengmeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032820759","display_name":"Xi Peng","orcid":"https://orcid.org/0000-0003-3809-5386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Xi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100329338"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9894000291824341,"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":0.9894000291824341,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9743000268936157,"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":0.9711999893188477,"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/robustness","display_name":"Robustness (evolution)","score":0.7293132543563843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.721724808216095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6159303784370422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872454047203064},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5577921271324158},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.489065021276474},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4540763795375824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3217507004737854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15496739745140076}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7293132543563843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721724808216095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6159303784370422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872454047203064},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5577921271324158},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.489065021276474},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4540763795375824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3217507004737854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15496739745140076},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2303.16390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.16390","pdf_url":"https://arxiv.org/pdf/2303.16390","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2303.16390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.16390","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":"pmh:oai:arXiv.org:2303.16390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.16390","pdf_url":"https://arxiv.org/pdf/2303.16390","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307084","display_name":"University of Delaware Research Foundation","ror":"https://ror.org/01sbq1a82"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4361806472.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W3162204513","https://openalex.org/W2094012830","https://openalex.org/W187246281"],"abstract_inverted_index":{"As":[0],"black-box":[1],"models":[2,19],"increasingly":[3],"power":[4],"high-stakes":[5],"applications,":[6],"a":[7,118],"variety":[8],"of":[9,100,121,150],"data-driven":[10,31],"explanation":[11,151],"methods":[12],"have":[13],"been":[14],"introduced.":[15],"Meanwhile,":[16],"machine":[17],"learning":[18,73,99],"are":[20],"constantly":[21],"challenged":[22],"by":[23,84],"distributional":[24,54,156],"shifts.":[25,55,157],"A":[26],"question":[27],"naturally":[28],"arises:":[29],"Are":[30],"explanations":[32,52,60,101,107],"robust":[33,59,106],"against":[34,61,155],"out-of-distribution":[35,62],"data?":[36,63],"Our":[37,136],"empirical":[38],"results":[39,137],"show":[40],"that":[41,139],"even":[42],"though":[43],"predict":[44],"correctly,":[45],"the":[46,90,98,109,140,145],"model":[47],"might":[48],"still":[49],"yield":[50],"unreliable":[51],"under":[53],"How":[56],"to":[57,87,93],"develop":[58],"To":[64],"address":[65],"this":[66],"problem,":[67],"we":[68],"propose":[69],"an":[70],"end-to-end":[71],"model-agnostic":[72],"framework":[74],"Distributionally":[75],"Robust":[76],"Explanations":[77],"(DRE).":[78],"The":[79],"key":[80],"idea":[81],"is,":[82],"inspired":[83],"self-supervised":[85],"learning,":[86],"fully":[88],"utilizes":[89],"inter-distribution":[91],"information":[92],"provide":[94],"supervisory":[95],"signals":[96],"for":[97],"without":[102],"human":[103],"annotation.":[104],"Can":[105],"benefit":[108],"model's":[110,146],"generalization":[111],"capability?":[112],"We":[113],"conduct":[114],"extensive":[115],"experiments":[116],"on":[117,130],"wide":[119],"range":[120],"tasks":[122],"and":[123,128,132,152],"data":[124],"types,":[125],"including":[126],"classification":[127],"regression":[129],"image":[131],"scientific":[133],"tabular":[134],"data.":[135],"demonstrate":[138],"proposed":[141],"method":[142],"significantly":[143],"improves":[144],"performance":[147],"in":[148],"terms":[149],"prediction":[153],"robustness":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}