{"id":"https://openalex.org/W4382049226","doi":"https://doi.org/10.1145/3583678.3596891","title":"Adaptive Distributed Streaming Similarity Joins","display_name":"Adaptive Distributed Streaming Similarity Joins","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382049226","doi":"https://doi.org/10.1145/3583678.3596891"},"language":"en","primary_location":{"id":"doi:10.1145/3583678.3596891","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583678.3596891","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583678.3596891","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583678.3596891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005536774","display_name":"George Siachamis","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"George Siachamis","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073692540","display_name":"Kyriakos Psarakis","orcid":"https://orcid.org/0000-0002-3017-5704"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kyriakos Psarakis","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019968638","display_name":"Marios Fragkoulis","orcid":"https://orcid.org/0000-0002-0160-0855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marios Fragkoulis","raw_affiliation_strings":["Delivery Hero SE, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Delivery Hero SE, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176667","display_name":"Odysseas Papapetrou","orcid":"https://orcid.org/0000-0003-0477-4399"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odysseas Papapetrou","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090401584","display_name":"Arie van Deursen","orcid":"https://orcid.org/0000-0003-4850-3312"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arie van Deursen","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002932353","display_name":"Asterios Katsifodimos","orcid":"https://orcid.org/0000-0002-6717-2945"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Asterios Katsifodimos","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005536774"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.3457,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64437165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998999834060669,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9998999834060669,"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/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9596856832504272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250414133071899},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5860460996627808},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5340232849121094},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47365009784698486},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.4563189148902893},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4448944926261902},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4446297883987427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44346627593040466},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3518224060535431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14315378665924072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09777992963790894},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.08222377300262451}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9596856832504272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250414133071899},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5860460996627808},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5340232849121094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47365009784698486},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.4563189148902893},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4448944926261902},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4446297883987427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44346627593040466},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3518224060535431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14315378665924072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09777992963790894},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.08222377300262451},{"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3583678.3596891","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583678.3596891","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583678.3596891","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/3aa2ebdb-1b3a-429a-ae67-305000696cfc","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/3aa2ebdb-1b3a-429a-ae67-305000696cfc","pdf_url":"https://pure.tue.nl/ws/files/353005391/3583678.3596891.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Siachamis, G, Psarakis, K, Fragkoulis, M, Papapetrou, O, van Deursen, A & Katsifodimos, A 2023, Adaptive Distributed Streaming Similarity Joins. in DEBS '23 : Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems. Association for Computing Machinery, Inc., New York, pp. 25-36, 17th ACM International Conference on Distributed and Event-based Systems, DEBS 2023, Neuchatel, Switzerland, 27/06/23. https://doi.org/10.1145/3583678.3596891","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:tudelft.nl:uuid:7110874a-a227-4407-a35e-7f78e4b2d8b8","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:7110874a-a227-4407-a35e-7f78e4b2d8b8","pdf_url":"https://repository.tudelft.nl/file/File_8f2d633f-fd53-4644-8f0c-f907eb57d02b","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3583678.3596891","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583678.3596891","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583678.3596891","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4918171799","display_name":null,"funder_award_id":"19708","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G5741899482","display_name":null,"funder_award_id":"101070122","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6434866206","display_name":"Spatio-TEmporal Linked data tools for the AgRi-food data space","funder_award_id":"101070122","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382049226.pdf","grobid_xml":"https://content.openalex.org/works/W4382049226.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2001700730","https://openalex.org/W2008888174","https://openalex.org/W2010003189","https://openalex.org/W2028506488","https://openalex.org/W2054498531","https://openalex.org/W2075620950","https://openalex.org/W2076211799","https://openalex.org/W2104599107","https://openalex.org/W2125671345","https://openalex.org/W2129553531","https://openalex.org/W2133546152","https://openalex.org/W2143851345","https://openalex.org/W2151930506","https://openalex.org/W2165647619","https://openalex.org/W2169070268","https://openalex.org/W2169795703","https://openalex.org/W2170522656","https://openalex.org/W2172286195","https://openalex.org/W2270660075","https://openalex.org/W2296107147","https://openalex.org/W2555648367","https://openalex.org/W2612210001","https://openalex.org/W2803443244","https://openalex.org/W2883952940","https://openalex.org/W2898352726","https://openalex.org/W2934540250","https://openalex.org/W2938070826","https://openalex.org/W2945594129","https://openalex.org/W2952479794","https://openalex.org/W2963852054","https://openalex.org/W3008872465","https://openalex.org/W3174896615","https://openalex.org/W4285335450"],"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/W2104496206","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W3013303285","https://openalex.org/W2385836742"],"abstract_inverted_index":{"How":[0],"can":[1,84],"we":[2,17,60],"perform":[3],"similarity":[4,34,55,67,99],"joins":[5,35],"of":[6,53,78,89,94,112,127,132],"multi-dimensional":[7,79],"streams":[8,21],"in":[9,22,91,101,130],"a":[10,125],"distributed":[11,65],"fashion,":[12],"achieving":[13],"low":[14],"latency?":[15],"Can":[16],"adaptively":[18,85],"repartition":[19],"those":[20],"order":[23],"to":[24,33,39,48],"retain":[25],"high":[26],"performance":[27],"under":[28],"concept":[29,95],"drifts?":[30],"Current":[31],"approaches":[32],"are":[36],"either":[37],"restricted":[38],"single-node":[40],"deployments":[41],"or":[42],"focus":[43],"on":[44,110,124],"set-similarity":[45],"joins,":[46],"failing":[47],"cover":[49],"the":[50,62,87,92,102],"ubiquitous":[51],"case":[52,93],"metric-space":[54],"joins.":[56],"In":[57],"this":[58],"paper,":[59],"propose":[61],"first":[63],"adaptive":[64],"streaming":[66],"join":[68],"approach":[69,83,109],"that":[70],"gracefully":[71],"scales":[72],"with":[73],"variable":[74],"velocity":[75],"and":[76,115,120,136],"distribution":[77],"data":[80,118,137],"streams.":[81],"Our":[82],"rebalance":[86],"load":[88,121],"nodes":[90],"drifts,":[96],"allowing":[97],"for":[98],"computations":[100],"general":[103],"metric":[104],"space.":[105],"We":[106],"implement":[107],"our":[108],"top":[111],"Apache":[113],"Flink":[114],"evaluate":[116],"its":[117],"partitioning":[119],"balancing":[122],"schemes":[123],"set":[126],"synthetic":[128],"datasets":[129],"terms":[131],"latency,":[133],"comparisons":[134],"ratio,":[135],"duplication":[138],"ratio.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}