{"id":"https://openalex.org/W2551009015","doi":"https://doi.org/10.1109/bigdata.2016.7841024","title":"\u201cInfluence sketching\u201d: Finding influential samples in large-scale regressions","display_name":"\u201cInfluence sketching\u201d: Finding influential samples in large-scale regressions","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2551009015","doi":"https://doi.org/10.1109/bigdata.2016.7841024","mag":"2551009015"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1611.05923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078188028","display_name":"Mike Wojnowicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mike Wojnowicz","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031301792","display_name":"B. Cruz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Cruz","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626936","display_name":"Xuan Zhao","orcid":"https://orcid.org/0000-0001-8517-0276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Zhao","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056908426","display_name":"Brian Wallace","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Wallace","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090137872","display_name":"Matt Wolff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Wolff","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056213690","display_name":"Jay Luan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Luan","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082285843","display_name":"Crable Caleb","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caleb Crable","raw_affiliation_strings":["Department of Research and Intelligence Cylance, Inc., Irvine, California 92612"],"affiliations":[{"raw_affiliation_string":"Department of Research and Intelligence Cylance, Inc., Irvine, California 92612","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078188028"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5473,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93990271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2016","issue":null,"first_page":"3601","last_page":"3612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9973000288009644,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973000288009644,"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/T10057","display_name":"Face and Expression Recognition","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/scale","display_name":"Scale (ratio)","score":0.6164387464523315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5599749088287354},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10375097393989563},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07546126842498779}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6164387464523315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5599749088287354},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10375097393989563},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07546126842498779}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2016.7841024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1611.05923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.05923","pdf_url":"https://arxiv.org/pdf/1611.05923","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:2785417769","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702224571678468","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1611.05923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.05923","pdf_url":"https://arxiv.org/pdf/1611.05923","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1992129502","https://openalex.org/W1999352252","https://openalex.org/W2000159976","https://openalex.org/W2020214980","https://openalex.org/W2037757210","https://openalex.org/W2041836310","https://openalex.org/W2117756735","https://openalex.org/W2138145347","https://openalex.org/W2167460663","https://openalex.org/W2951501516","https://openalex.org/W2951863880","https://openalex.org/W2963385925","https://openalex.org/W4233620411","https://openalex.org/W4241313018","https://openalex.org/W4299689471","https://openalex.org/W4302439603"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"There":[0],"is":[1,116],"an":[2,31],"especially":[3,212],"strong":[4],"need":[5],"in":[6,40,111],"modern":[7],"large-scale":[8],"data":[9],"analysis":[10],"to":[11,36,47,81,86,146,182,203,214,235],"prioritize":[12],"samples":[13,25,46,64,141,174,190,210],"for":[14,62],"manual":[15],"inspection.":[16],"For":[17,163],"example,":[18,164],"the":[19,38,41,69,108,113,119,124,144,186,200,218,224],"inspection":[20],"could":[21],"target":[22],"important":[23],"mislabeled":[24],"or":[26],"key":[27],"vulnerabilities":[28],"exploitable":[29],"by":[30,142],"adversarial":[32],"attack.":[33],"In":[34,79,217],"order":[35,80],"solve":[37],"\u201cneedle":[39],"haystack\u201d":[42],"problem":[43],"of":[44,55,71,151,172,189,240],"which":[45,65,97],"inspect,":[48],"we":[49,92,98,165,206,221],"develop":[50],"a":[51,58,72,94,147],"new":[52,95],"scalable":[53],"version":[54],"Cook's":[56],"distance,":[57],"classical":[59],"statistical":[60],"technique":[61,84,145],"identifying":[63],"unusually":[66],"strongly":[67],"impact":[68],"fit":[70],"regression":[73],"model":[74],"(and":[75],"its":[76],"downstream":[77],"predictions).":[78],"scale":[82],"this":[83],"up":[85],"very":[87],"large":[88],"and":[89,137,228],"high-dimensional":[90],"datasets,":[91],"introduce":[93],"algorithm":[96],"call":[99],"\u201cinfluence":[100],"sketching.\u201d":[101],"Influence":[102],"sketching":[103,134,232],"embeds":[104],"random":[105],"projections":[106],"within":[107],"influence":[109,114,133,193,231],"computation;":[110],"particular,":[112],"score":[115],"calculated":[117],"using":[118],"randomly":[120,168],"projected":[121],"pseudo-dataset":[122],"from":[123,180],"post-convergence":[125],"General":[126],"Linear":[127],"Model":[128],"(GLM).":[129],"We":[130],"validate":[131],"that":[132,167,208,230],"can":[135],"reliably":[136],"successfully":[138],"discover":[139],"influential":[140,209,226],"applying":[143],"malware":[148],"detection":[149],"dataset":[150],"over":[152],"2":[153],"million":[154],"executable":[155],"files,":[156],"each":[157],"represented":[158],"with":[159,191],"almost":[160],"100,000":[161],"features.":[162],"find":[166,207,229],"deleting":[169,185],"approximately":[170],"10%":[171],"training":[173],"reduces":[175,196],"predictive":[176,197],"accuracy":[177,198],"only":[178],"slightly":[179],"99.47%":[181],"99.45%,":[183],"whereas":[184],"same":[187],"number":[188],"high":[192],"sketch":[194],"scores":[195],"all":[199],"way":[201],"down":[202],"90.24%.":[204],"Moreover,":[205],"are":[211],"likely":[213],"be":[215],"mislabeled.":[216],"case":[219],"study,":[220],"manually":[222],"inspect":[223],"most":[225],"samples,":[227],"pointed":[233],"us":[234],"new,":[236],"previously":[237],"unidentified":[238],"pieces":[239],"malware.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}