{"id":"https://openalex.org/W2116448239","doi":"https://doi.org/10.1145/1015330.1015399","title":"A needle in a haystack","display_name":"A needle in a haystack","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2116448239","doi":"https://doi.org/10.1145/1015330.1015399","mag":"2116448239"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015399","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","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/A5006419939","display_name":"Koby Crammer","orcid":"https://orcid.org/0000-0001-8824-5747"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Koby Crammer","raw_affiliation_strings":["The Hebrew University of Jerusalem, Jerusalem, Israel","The Hebrew University of Jerusalem , Jerusalem , Israel"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006419939"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":6.2959,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96333943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9962999820709229,"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":0.9962999820709229,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9923999905586243,"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":0.983299970626831,"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/haystack","display_name":"Haystack","score":0.891586184501648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290155291557312},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6389879584312439},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5531071424484253},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48960429430007935},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47606390714645386},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.45860159397125244},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.44765719771385193},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.4427371919155121},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.430502712726593},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41100260615348816},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40608593821525574},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37999966740608215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3366566300392151},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27070558071136475},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.14217045903205872}],"concepts":[{"id":"https://openalex.org/C13424479","wikidata":"https://www.wikidata.org/wiki/Q5687237","display_name":"Haystack","level":2,"score":0.891586184501648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290155291557312},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6389879584312439},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5531071424484253},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48960429430007935},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47606390714645386},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.45860159397125244},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.44765719771385193},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.4427371919155121},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.430502712726593},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41100260615348816},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40608593821525574},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37999966740608215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3366566300392151},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27070558071136475},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.14217045903205872},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1015330.1015399","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W16591383","https://openalex.org/W1504361335","https://openalex.org/W1548139318","https://openalex.org/W1592753633","https://openalex.org/W1943383135","https://openalex.org/W2132870739","https://openalex.org/W2147246240","https://openalex.org/W2979454998","https://openalex.org/W3035139526"],"related_works":["https://openalex.org/W1504394672","https://openalex.org/W2622284819","https://openalex.org/W3089381707","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103","https://openalex.org/W2304083841","https://openalex.org/W2362448732"],"abstract_inverted_index":{"This":[0,18],"paper":[1,96],"addresses":[2],"the":[3,65,125,129,137,163],"problem":[4,83,135,146],"of":[5,12,49,92,110,124,165],"finding":[6,52],"a":[7,15,31,46,89,107,116,158],"small":[8,108],"and":[9,87,150,157],"coherent":[10],"subset":[11],"points":[13,39,61],"in":[14,45,70],"given":[16],"data.":[17,126],"problem,":[19],"sometimes":[20],"referred":[21],"to":[22,29,54,64,81,105,142],"as":[23,36,40,132],"one-class":[24],"or":[25,69],"set":[26,91,109],"covering,":[27],"requires":[28],"find":[30,106],"small-radius":[32],"ball":[33],"that":[34,119],"covers":[35],"many":[37,59],"data":[38,60,156],"possible.":[41],"It":[42],"rises":[43],"naturally":[44],"wide":[47],"range":[48],"applications,":[50],"from":[51],"gene-modules":[53],"extracting":[55],"documents'":[56],"topics,":[57],"where":[58,72],"are":[62,76],"irrelevant":[63],"task":[66,131],"at":[67],"hand,":[68],"applications":[71],"only":[73],"positive":[74],"examples":[75],"available.":[77],"Most":[78],"previous":[79],"approaches":[80],"this":[82,95,144],"focus":[84],"on":[85,121,153],"identifying":[86],"discarding":[88],"possible":[90],"outliers.":[93],"In":[94],"we":[97],"adopt":[98],"an":[99,133],"opposite":[100],"approach":[101],"which":[102],"directly":[103],"aims":[104],"coherently":[111],"structured":[112],"regions,":[113],"by":[114],"using":[115,136],"loss":[117],"function":[118],"focuses":[120],"local":[122],"properties":[123],"We":[127],"formalize":[128],"learning":[130],"optimization":[134,145],"Information-Bottleneck":[138],"principle.":[139],"An":[140],"algorithm":[141],"solve":[143],"is":[147],"then":[148],"derived":[149],"analyzed.":[151],"Experiments":[152],"gene":[154],"expression":[155],"text":[159],"document":[160],"corpus":[161],"demonstrate":[162],"merits":[164],"our":[166],"approach.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}