{"id":"https://openalex.org/W4384392944","doi":"https://doi.org/10.48550/arxiv.2307.06913","title":"Uncovering Unique Concept Vectors through Latent Space Decomposition","display_name":"Uncovering Unique Concept Vectors through Latent Space Decomposition","publication_year":2023,"publication_date":"2023-07-13","ids":{"openalex":"https://openalex.org/W4384392944","doi":"https://doi.org/10.48550/arxiv.2307.06913"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.06913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.06913","pdf_url":"https://arxiv.org/pdf/2307.06913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2307.06913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041248487","display_name":"Mara Graziani","orcid":"https://orcid.org/0000-0003-3456-945X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Graziani, Mara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092474639","display_name":"Laura O' Mahony","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahony, Laura O'","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081134111","display_name":"An-phi Nguyen","orcid":"https://orcid.org/0000-0003-4998-5931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, An-Phi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061961859","display_name":"Henning M\u00fcller","orcid":"https://orcid.org/0000-0001-6800-9878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00fcller, Henning","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007157109","display_name":"Vincent Andrearczyk","orcid":"https://orcid.org/0000-0003-0793-5821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrearczyk, Vincent","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041248487"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9958000183105469,"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":0.9958000183105469,"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":0.975600004196167,"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":0.9725000262260437,"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":0.8442866802215576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521675825119019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6475570797920227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5742136240005493},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5275998711585999},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5178097486495972},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4914313554763794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4894782304763794},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44777601957321167},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4442421793937683},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44343826174736023},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4373510479927063},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4306909441947937},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42416250705718994},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34429875016212463}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8442866802215576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521675825119019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475570797920227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5742136240005493},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5275998711585999},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5178097486495972},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4914313554763794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4894782304763794},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44777601957321167},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4442421793937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44343826174736023},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4373510479927063},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4306909441947937},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42416250705718994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34429875016212463},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.06913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.06913","pdf_url":"https://arxiv.org/pdf/2307.06913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.06913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.06913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.06913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.06913","pdf_url":"https://arxiv.org/pdf/2307.06913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Interpreting":[0],"the":[1,39,42,46,49,53,68,78,107,122,138,145,185,190],"inner":[2],"workings":[3],"of":[4,81,100,124,148,187,192,194],"deep":[5,72],"learning":[6],"models":[7,73],"is":[8,26],"crucial":[9],"for":[10,41],"establishing":[11],"trust":[12],"and":[13,87,110,134,178,181,189],"ensuring":[14],"model":[15,108,179],"safety.":[16],"Concept-based":[17],"explanations":[18,47],"have":[19],"emerged":[20],"as":[21,34],"a":[22,60,82],"superior":[23],"approach":[24],"that":[25,65,103,111,121],"more":[27],"interpretable":[28],"than":[29],"feature":[30],"attribution":[31],"estimates":[32],"such":[33],"pixel":[35],"saliency.":[36],"However,":[37],"defining":[38],"concepts":[40,69,126],"interpretability":[43],"analysis":[44],"biases":[45,188],"by":[48,71,90,164],"user's":[50],"expectations":[51],"on":[52],"concepts.":[54,116],"To":[55],"address":[56],"this,":[57],"we":[58,93,143],"propose":[59],"novel":[61,169],"post-hoc":[62],"unsupervised":[63,91],"method":[64,150],"automatically":[66],"uncovers":[67],"learned":[70],"during":[74],"training.":[75],"By":[76],"decomposing":[77],"latent":[79],"space":[80],"layer":[83],"in":[84,151],"singular":[85],"vectors":[86,96,157],"refining":[88],"them":[89],"clustering,":[92],"uncover":[94],"concept":[95,156],"aligned":[97],"with":[98],"directions":[99],"high":[101],"variance":[102],"are":[104,127],"relevant":[105],"to":[106,113,130,137,175],"prediction,":[109],"point":[112],"semantically":[114],"distinct":[115],"Our":[117],"extensive":[118],"experiments":[119],"reveal":[120],"majority":[123],"our":[125,149,155],"readily":[128],"understandable":[129],"humans,":[131],"exhibit":[132],"coherency,":[133],"bear":[135],"relevance":[136],"task":[139],"at":[140],"hand.":[141],"Moreover,":[142],"showcase":[144],"practical":[146],"utility":[147],"dataset":[152],"exploration,":[153],"where":[154],"successfully":[158],"identify":[159],"outlier":[160],"training":[161,197],"samples":[162],"affected":[163],"various":[165],"confounding":[166],"factors.":[167],"This":[168],"exploration":[170],"technique":[171],"has":[172],"remarkable":[173],"versatility":[174],"data":[176],"types":[177],"architectures":[180],"it":[182],"will":[183],"facilitate":[184],"identification":[186],"discovery":[191],"sources":[193],"error":[195],"within":[196],"data.":[198]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}