{"id":"https://openalex.org/W2109749916","doi":"https://doi.org/10.1145/1008992.1009012","title":"Locality preserving indexing for document representation","display_name":"Locality preserving indexing for document representation","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2109749916","doi":"https://doi.org/10.1145/1008992.1009012","mag":"2109749916"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007759001","display_name":"Haifeng Liu","orcid":"https://orcid.org/0000-0002-3619-1211"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haifeng Liu","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102013345"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":14.326,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.988458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9965000152587891,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9909999966621399,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.834705114364624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473970651626587},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7209087610244751},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5911275148391724},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5887990593910217},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5492522716522217},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.54721999168396},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4336385428905487},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.42337656021118164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4141808748245239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41061919927597046},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39255741238594055},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.3625662326812744}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.834705114364624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473970651626587},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7209087610244751},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5911275148391724},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5887990593910217},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5492522716522217},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.54721999168396},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4336385428905487},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.42337656021118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4141808748245239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41061919927597046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39255741238594055},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3625662326812744},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1008992.1009012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.3593","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.3593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.cs.uchicago.edu/~xiaofei/SIGIR2004_HE.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.3327","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.3327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.cs.uchicago.edu/%7Exiaofei/conference-23.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.4101","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.4101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.microsoft.com/asia/dload_files/group/ims/23.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1490760466","https://openalex.org/W1493526108","https://openalex.org/W1564947197","https://openalex.org/W1578099820","https://openalex.org/W1956559956","https://openalex.org/W1964563026","https://openalex.org/W1965452491","https://openalex.org/W1969839048","https://openalex.org/W2001141328","https://openalex.org/W2013029404","https://openalex.org/W2048929541","https://openalex.org/W2053186076","https://openalex.org/W2056029990","https://openalex.org/W2063392856","https://openalex.org/W2080051508","https://openalex.org/W2089497633","https://openalex.org/W2099708568","https://openalex.org/W2107743791","https://openalex.org/W2132988481","https://openalex.org/W2147152072","https://openalex.org/W2154872931","https://openalex.org/W2155602043","https://openalex.org/W2156718197","https://openalex.org/W2325227998","https://openalex.org/W2572321817","https://openalex.org/W2799061466","https://openalex.org/W2999905431","https://openalex.org/W4233135949","https://openalex.org/W4244494905","https://openalex.org/W6640862754","https://openalex.org/W6682644385"],"related_works":["https://openalex.org/W185474625","https://openalex.org/W2165612380","https://openalex.org/W187510616","https://openalex.org/W1500125366","https://openalex.org/W2551770406","https://openalex.org/W1557970708","https://openalex.org/W2137763598","https://openalex.org/W2611108488","https://openalex.org/W1575842006","https://openalex.org/W1996059221"],"abstract_inverted_index":{"Document":[0],"representation":[1,41,109,137],"and":[2,11,17,104],"indexing":[3],"is":[4,24,71,78],"a":[5,63,81,106],"key":[6],"problem":[7],"for":[8,39,73],"document":[9,40,74,77,97,108],"analysis":[10],"processing,":[12],"such":[13,29],"as":[14],"clustering,":[15],"classification":[16],"retrieval.":[18],"Conventionally,":[19],"Latent":[20],"Semantic":[21],"Indexing":[22,69],"(LSI)":[23],"considered":[25],"effective":[26],"in":[27,54,138],"deriving":[28],"an":[30],"indexing.":[31,75],"LSI":[32,49,89,125],"essentially":[33],"detects":[34,113],"the":[35,44,92,96,101,114,120,139],"most":[36,45],"representative":[37],"features":[38],"rather":[42],"than":[43],"discriminative":[46],"features.":[47],"Therefore,":[48],"might":[50],"not":[51],"be":[52],"optimal":[53],"discriminating":[55],"documents":[56],"with":[57,83,124],"different":[58],"semantics.":[59],"In":[60,86],"this":[61],"paper,":[62],"novel":[64],"algorithm":[65],"called":[66],"Locality":[67],"Preserving":[68],"(LPI)":[70],"proposed":[72,121],"Each":[76],"represented":[79],"by":[80],"vector":[82],"low":[84],"dimensionality.":[85],"contrast":[87],"to":[88],"which":[90],"discovers":[91,100],"global":[93],"structure":[94,103],"of":[95,141],"space,":[98],"LPI":[99,122,134],"local":[102],"obtains":[105],"compact":[107],"subspace":[110],"that":[111,133],"best":[112],"essential":[115],"semantic":[116,142],"structure.":[117,143],"We":[118],"compare":[119],"approach":[123],"on":[126],"two":[127],"standard":[128],"databases.":[129],"Experimental":[130],"results":[131],"show":[132],"provides":[135],"better":[136],"sense":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}