{"id":"https://openalex.org/W4205951478","doi":"https://doi.org/10.1109/bigdata52589.2021.9671497","title":"Natural Joins for Schema-free Data","display_name":"Natural Joins for Schema-free Data","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205951478","doi":"https://doi.org/10.1109/bigdata52589.2021.9671497"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671497","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5075220789","display_name":"Damjan Gjurovski","orcid":"https://orcid.org/0000-0002-1296-5745"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Damjan Gjurovski","raw_affiliation_strings":["TU Kaiserslautern (TUK), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern (TUK), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043223305","display_name":"Sebastian Michel","orcid":"https://orcid.org/0000-0001-6636-2694"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Michel","raw_affiliation_strings":["TU Kaiserslautern (TUK), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern (TUK), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075220789"],"corresponding_institution_ids":["https://openalex.org/I153267046"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17193332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2372","last_page":"2380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.9076917767524719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8821032643318176},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8444668650627136},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5765647888183594},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4673120677471161},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.4498639404773712},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.4164116680622101},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38353487849235535},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36727383732795715},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3646774888038635},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34515851736068726},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.30326351523399353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24687525629997253},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.09126660227775574}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.9076917767524719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8821032643318176},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8444668650627136},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5765647888183594},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4673120677471161},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.4498639404773712},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.4164116680622101},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38353487849235535},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36727383732795715},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3646774888038635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34515851736068726},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.30326351523399353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24687525629997253},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.09126660227775574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671497","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W42901544","https://openalex.org/W2003515726","https://openalex.org/W2004772832","https://openalex.org/W2007030756","https://openalex.org/W2011716962","https://openalex.org/W2014332937","https://openalex.org/W2043934800","https://openalex.org/W2103207352","https://openalex.org/W2122048769","https://openalex.org/W2125529470","https://openalex.org/W2162098589","https://openalex.org/W2181714304","https://openalex.org/W2280236292","https://openalex.org/W2292693431","https://openalex.org/W2992058379","https://openalex.org/W3030533359","https://openalex.org/W3031681876","https://openalex.org/W3173993340","https://openalex.org/W4252403066","https://openalex.org/W6601775268","https://openalex.org/W6685518766","https://openalex.org/W6695145194"],"related_works":["https://openalex.org/W2087376388","https://openalex.org/W2103472145","https://openalex.org/W2092058806","https://openalex.org/W1561927997","https://openalex.org/W1992271858","https://openalex.org/W166845585","https://openalex.org/W2042840812","https://openalex.org/W4238907651","https://openalex.org/W1591654213","https://openalex.org/W2153512431"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,77],"propose":[4,41],"an":[5],"efficient":[6],"approach":[7],"for":[8,61],"computing":[9],"natural":[10],"joins":[11],"over":[12,84],"schema-free":[13],"JSON":[14,55],"documents.":[15],"We":[16,40],"argue":[17],"that":[18,79],"traditional":[19,90],"hash-":[20],"and":[21,57,74,98],"sort-based":[22],"approaches":[23,87],"are":[24],"inapplicable":[25],"as":[26],"shared":[27],"attributes":[28],"between":[29],"documents":[30,56],"can":[31],"vary,":[32],"given":[33],"the":[34,54,63,85],"lack":[35],"of":[36,53,95],"a":[37,43,50],"fixed":[38],"schema.":[39],"using":[42],"frequent":[44],"pattern":[45],"tree":[46],"(FP-tree)":[47],"to":[48,66],"store":[49],"compact":[51],"representation":[52],"present":[58],"two":[59],"algorithms":[60],"traversing":[62],"constituent":[64],"nodes":[65],"identify":[67],"results.":[68],"Through":[69],"extensive":[70],"experiments":[71],"on":[72],"real-world":[73],"synthetic":[75],"datasets,":[76],"show":[78],"they":[80],"have":[81],"superior":[82],"performance":[83],"join":[86],"used":[88],"in":[89,93],"database":[91],"systems":[92],"terms":[94],"execution":[96],"time":[97],"memory":[99],"consumption.":[100]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}