{"id":"https://openalex.org/W2914123175","doi":"https://doi.org/10.1109/bigdata.2018.8622338","title":"Efficient Dimensionality Reduction for Sparse Binary Data","display_name":"Efficient Dimensionality Reduction for Sparse Binary Data","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914123175","doi":"https://doi.org/10.1109/bigdata.2018.8622338","mag":"2914123175"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/A5031238051","display_name":"Rameshwar Pratap","orcid":"https://orcid.org/0000-0002-8824-6202"},"institutions":[{"id":"https://openalex.org/I19149307","display_name":"Chennai Mathematical Institute","ror":"https://ror.org/04zp24820","country_code":"IN","type":"education","lineage":["https://openalex.org/I19149307"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rameshwar Pratap","raw_affiliation_strings":["Chennai Mathematical Institute (CMI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chennai Mathematical Institute (CMI)","institution_ids":["https://openalex.org/I19149307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109451514","display_name":"Raghav Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I19149307","display_name":"Chennai Mathematical Institute","ror":"https://ror.org/04zp24820","country_code":"IN","type":"education","lineage":["https://openalex.org/I19149307"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghav Kulkarni","raw_affiliation_strings":["Chennai Mathematical Institute (CMI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chennai Mathematical Institute (CMI)","institution_ids":["https://openalex.org/I19149307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025856708","display_name":"Ishan Sohony","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ishan Sohony","raw_affiliation_strings":["Stony Brook University, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, NY","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68645083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987999796867371,"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/T10057","display_name":"Face and Expression Recognition","score":0.9975000023841858,"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/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.713841438293457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6597090363502502},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.5383720397949219},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5135338306427002},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5099276304244995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48537003993988037},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.4753275215625763},{"id":"https://openalex.org/keywords/binary-data","display_name":"Binary data","score":0.4254012703895569},{"id":"https://openalex.org/keywords/diffusion-map","display_name":"Diffusion map","score":0.42332369089126587},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.41928544640541077},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4112066924571991},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4100153148174286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31705114245414734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27703040838241577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24413660168647766},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.22335821390151978},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0849202573299408}],"concepts":[{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.713841438293457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597090363502502},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.5383720397949219},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5135338306427002},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5099276304244995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48537003993988037},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.4753275215625763},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.4254012703895569},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.42332369089126587},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.41928544640541077},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4112066924571991},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4100153148174286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31705114245414734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27703040838241577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24413660168647766},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.22335821390151978},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0849202573299408},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1455310343","https://openalex.org/W1502916507","https://openalex.org/W1506285740","https://openalex.org/W1991800036","https://openalex.org/W2060170830","https://openalex.org/W2088101210","https://openalex.org/W2147717514","https://openalex.org/W2149230623","https://openalex.org/W2261895596","https://openalex.org/W2301752323","https://openalex.org/W2951895957","https://openalex.org/W2963733740","https://openalex.org/W2979473749","https://openalex.org/W3120740533","https://openalex.org/W6629956336","https://openalex.org/W6630198464","https://openalex.org/W6697989621","https://openalex.org/W6742706486","https://openalex.org/W6769341872"],"related_works":["https://openalex.org/W2060170830","https://openalex.org/W4210792548","https://openalex.org/W2954525245","https://openalex.org/W2953192649","https://openalex.org/W2105734423","https://openalex.org/W3163698500","https://openalex.org/W2529763060","https://openalex.org/W2914123175","https://openalex.org/W3003717980","https://openalex.org/W2979297384"],"abstract_inverted_index":{"We":[0,117],"propose":[1],"a":[2,17,119],"dimensionality":[3,96,125],"reduction":[4,126],"(sketching)":[5],"algorithm":[6,15,78,105,136],"for":[7],"high":[8],"dimensional,":[9],"sparse,":[10],"binary":[11,89],"data.":[12],"Our":[13,77,104,134],"proposed":[14,135],"provides":[16],"single":[18],"sketch":[19,101],"which":[20,98],"simultaneously":[21],"preserves":[22,87],"multiple":[23],"similarity":[24],"measures":[25],"including":[26],"Hamming":[27],"distance,":[28],"Inner":[29],"product,":[30],"and":[31,56,85,113,128,139],"Jaccard":[32],"Similarity":[33],"[12].":[34],"In":[35],"contrast":[36],"to":[37,141],"the":[38,46,58,64,82,88,92,95,100,124],"\"local":[39],"projection\"":[40],"strategy":[41],"used":[42],"by":[43],"most":[44],"of":[45,91,123],"earlier":[47],"algorithms":[48],"[6],":[49],"[4],":[50],"[7],":[51],"our":[52],"approach":[53],"exploits":[54],"sparsity":[55],"combines":[57],"following":[59],"two":[60],"strategies:":[61],"1.":[62],"partitioning":[63],"dimensions":[65],"into":[66],"several":[67],"buckets,":[68],"2.":[69],"obtaining":[70],"\"global":[71],"linear":[72],"summaries\"":[73],"within":[74],"those":[75],"buckets.":[76],"is":[79,137],"faster":[80],"than":[81],"existing":[83],"state-of-the-art,":[84],"it":[86,130],"format":[90],"data":[93],"after":[94],"reduction,":[97],"makes":[99],"space":[102],"efficient.":[103],"can":[106],"also":[107],"be":[108],"easily":[109],"adapted":[110],"in":[111,143],"streaming":[112],"incremental":[114],"learning":[115],"frameworks.":[116],"give":[118],"rigorous":[120],"theoretical":[121],"analysis":[122],"bounds":[127],"complement":[129],"with":[131],"extensive":[132],"experiments.":[133],"simple":[138],"easy":[140],"implement":[142],"practice.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}