{"id":"https://openalex.org/W4398234812","doi":"https://doi.org/10.1145/3626246.3653370","title":"Similarity Joins of Sparse Features","display_name":"Similarity Joins of Sparse Features","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398234812","doi":"https://doi.org/10.1145/3626246.3653370"},"language":"en","primary_location":{"id":"doi:10.1145/3626246.3653370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/155773/1/3626246.3653370.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030261484","display_name":"Ahmed Metwally","orcid":"https://orcid.org/0000-0002-1084-8078"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed Metwally","raw_affiliation_strings":["Uber Technologies, Inc., Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Uber Technologies, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007650877","display_name":"Michael Shum","orcid":"https://orcid.org/0009-0009-3689-6113"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Shum","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030261484"],"corresponding_institution_ids":["https://openalex.org/I2946016260"],"apc_list":null,"apc_paid":null,"fwci":0.2468,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48042926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991999864578247,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991999864578247,"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/T11106","display_name":"Data Management and Algorithms","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9973999857902527,"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/joins","display_name":"Joins","score":0.8882550597190857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279884815216064},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6482554078102112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136980473995209},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38274848461151123},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3322484493255615},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07578593492507935}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8882550597190857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279884815216064},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6482554078102112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136980473995209},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38274848461151123},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3322484493255615},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07578593492507935},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626246.3653370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/155773","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/155773","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/155773/1/3626246.3653370.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/155773","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/155773","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/155773/1/3626246.3653370.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398234812.pdf","grobid_xml":"https://content.openalex.org/works/W4398234812.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W591429885","https://openalex.org/W1502916507","https://openalex.org/W1541936324","https://openalex.org/W1967838552","https://openalex.org/W1999092742","https://openalex.org/W2001700730","https://openalex.org/W2048779798","https://openalex.org/W2065259291","https://openalex.org/W2073167797","https://openalex.org/W2085491337","https://openalex.org/W2092961886","https://openalex.org/W2099194763","https://openalex.org/W2104599107","https://openalex.org/W2121516976","https://openalex.org/W2126907894","https://openalex.org/W2132399973","https://openalex.org/W2151930506","https://openalex.org/W2167847032","https://openalex.org/W2169795703","https://openalex.org/W2173213060","https://openalex.org/W2270660075","https://openalex.org/W2294331997","https://openalex.org/W2341744633","https://openalex.org/W2396588571","https://openalex.org/W2555576367","https://openalex.org/W2555648367","https://openalex.org/W2616120155","https://openalex.org/W2752274179","https://openalex.org/W2785764160","https://openalex.org/W2796341401","https://openalex.org/W2883952940","https://openalex.org/W2964071678","https://openalex.org/W3101111960","https://openalex.org/W3175308985","https://openalex.org/W3194653627","https://openalex.org/W4229641819","https://openalex.org/W4281388628","https://openalex.org/W6604386673","https://openalex.org/W6629956336","https://openalex.org/W6669696364","https://openalex.org/W6673784050","https://openalex.org/W6674576723","https://openalex.org/W6674599852","https://openalex.org/W6679663036","https://openalex.org/W6680450631","https://openalex.org/W6683401941","https://openalex.org/W6687322159","https://openalex.org/W6735844115","https://openalex.org/W6756129506","https://openalex.org/W6760665889","https://openalex.org/W6764604475","https://openalex.org/W6839017887"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Identifying":[0],"all":[1,118],"pairs":[2],"of":[3,36,53,95,130],"records":[4,40,70],"from":[5],"two":[6],"datasets":[7,153,174],"whose":[8],"similarity":[9],"exceeds":[10],"a":[11,92,155],"given":[12],"threshold":[13],"is":[14,25,57,67,159,166],"crucial":[15],"for":[16,133],"data":[17],"cleaning":[18],"and":[19,30,125,151,165],"clustering.":[20],"Our":[21],"work":[22],"on":[23,34,146,149,162],"similarity-joins":[24,35],"motivated":[26],"by":[27,78],"detecting":[28],"fraud":[29],"abuse.":[31],"We":[32],"focus":[33],"sparse":[37,42],"features,":[38],"where":[39],"represent":[41],"sets,":[43],"multisets,":[44],"or":[45,73],"vectors.":[46],"Most":[47],"state-of-the-art":[48],"techniques":[49],"are":[50,71,76],"distributed":[51],"versions":[52],"sequential":[54],"algorithms.":[55],"This":[56],"the":[58,65,69,101,109,114,128,167],"reason":[59],"they":[60],"fail":[61],"to":[62,106,117],"scale":[63],"when":[64],"alphabet":[66],"large,":[68,72],"some":[74],"elements":[75,111,116],"shared":[77],"numerous":[79],"records.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"propose":[85],"FastScalableSparseJoiner":[86,120],"(FSSJ)":[87],"that":[88,99,170],"introduces":[89],"quasi-prefix":[90],"filtering,":[91],"novel":[93],"flavor":[94],"prefix":[96],"filtering":[97],"[7]":[98],"exploits":[100],"skew":[102],"in":[103,141],"element":[104],"popularity":[105],"avoid":[107],"processing":[108],"most-popular":[110],"without":[112],"broadcasting":[113],"sorted":[115],"executors.":[119,136],"effectively":[121],"prunes":[122],"candidate":[123],"pairs,":[124],"efficiently":[126],"distributes":[127],"computation":[129],"partial":[131],"results":[132],"load-balancing":[134],"across":[135],"FSSJ":[137,158],"can":[138,171],"be":[139],"adopted":[140],"any":[142],"shared-nothing":[143],"architecture.":[144],"Based":[145],"our":[147],"evaluation":[148],"synthetic":[150],"real":[152],"using":[154],"Spark-based":[156],"implementation,":[157],"very":[160],"competitive":[161],"small":[163],"datasets,":[164],"only":[168],"algorithm":[169],"join":[172],"industry-scale":[173],"even":[175],"with":[176],"limited":[177],"resources.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}