{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:10:52Z","timestamp":1770959452763,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,11]],"date-time":"2018-10-11T00:00:00Z","timestamp":1539216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,11]]},"DOI":"10.1145\/3267809.3267834","type":"proceedings-article","created":{"date-parts":[[2018,9,28]],"date-time":"2018-09-28T18:00:41Z","timestamp":1538157641000},"page":"426-438","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["ApproxJoin"],"prefix":"10.1145","author":[{"given":"Do Le","family":"Quoc","sequence":"first","affiliation":[{"name":"TU Dresden, Germany"}]},{"given":"Istemi Ekin","family":"Akkus","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Germany"}]},{"given":"Pramod","family":"Bhatotia","sequence":"additional","affiliation":[{"name":"The University of Edinburgh, UK"}]},{"given":"Spyros","family":"Blanas","sequence":"additional","affiliation":[{"name":"The Ohio State University, USA"}]},{"given":"Ruichuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Germany"}]},{"given":"Christof","family":"Fetzer","sequence":"additional","affiliation":[{"name":"TU Dresden, Germany"}]},{"given":"Thorsten","family":"Strufe","sequence":"additional","affiliation":[{"name":"TU Dresden, Germany"}]}],"member":"320","published-online":{"date-parts":[[2018,10,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/flink.apache.org\/","author":"Flink Apache","year":"2018","unstructured":"Apache Flink . https:\/\/flink.apache.org\/ . Accessed : August , 2018 . Apache Flink. https:\/\/flink.apache.org\/. Accessed: August, 2018."},{"key":"e_1_3_2_1_2_1","volume-title":"http:\/\/hadoop.apache.org\/","author":"Hadoop Apache","year":"2018","unstructured":"Apache Hadoop . http:\/\/hadoop.apache.org\/ . Accessed : August , 2018 . Apache Hadoop. http:\/\/hadoop.apache.org\/. Accessed: August, 2018."},{"key":"e_1_3_2_1_3_1","volume-title":"https:\/\/spark.apache.org","author":"Spark Apache","year":"2018","unstructured":"Apache Spark . https:\/\/spark.apache.org . Accessed : August , 2018 . Apache Spark. https:\/\/spark.apache.org. Accessed: August, 2018."},{"key":"e_1_3_2_1_4_1","volume-title":"Accessed","author":"Approximate","year":"2018","unstructured":"Approximate query processing where do we go from here? http:\/\/wp.sigmod.org\/?p=2183 . Accessed : August , 2018 . Approximate query processing where do we go from here? http:\/\/wp.sigmod.org\/?p=2183. Accessed: August, 2018."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882940"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304581"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2593667"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465355"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1876037.1876087"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1924943.1924962"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735496.2735499"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2663165.2663334"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694371"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of USENIX Conference on File and Storage Technologies (FAST)","author":"Bhatotia P.","year":"2012","unstructured":"P. Bhatotia , R. Rodrigues , and A. Verma . Shredder: GPU-Accelerated Incremental Storage and Computation . In Proceedings of USENIX Conference on File and Storage Technologies (FAST) , 2012 . P. Bhatotia, R. Rodrigues, and A. Verma. Shredder: GPU-Accelerated Incremental Storage and Computation. In Proceedings of USENIX Conference on File and Storage Technologies (FAST), 2012."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the Conference on Hot Topics in Cloud Computing (HotCloud)","author":"Bhatotia P.","year":"2011","unstructured":"P. Bhatotia , A. Wieder , I. E. Akkus , R. Rodrigues , and U. A. Acar . Large-scale incremental data processing with change propagation . In Proceedings of the Conference on Hot Topics in Cloud Computing (HotCloud) , 2011 . P. Bhatotia, A. Wieder, I. E. Akkus, R. Rodrigues, and U. A. Acar. Large-scale incremental data processing with change propagation. In Proceedings of the Conference on Hot Topics in Cloud Computing (HotCloud), 2011."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038916.2038923"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"e_1_3_2_1_20_1","unstructured":"CAIDA. The CAIDA UCSD Anonymized Internet Traces 2015 (equinix-chicagodirA). http:\/\/www.caida.org\/data\/passive\/passive_2015_dataset.xml.  CAIDA. The CAIDA UCSD Anonymized Internet Traces 2015 (equinix-chicagodirA). http:\/\/www.caida.org\/data\/passive\/passive_2015_dataset.xml."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056097"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304206"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000004"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008935410038"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the International Conference on Very Large Data Bases (VLDB)","author":"Garofalakis M. N.","year":"2001","unstructured":"M. N. Garofalakis and P. B. Gibbon . Approximate Query Processing: Taming the TeraBytes . In Proceedings of the International Conference on Very Large Data Bases (VLDB) , 2001 . M. N. Garofalakis and P. B. Gibbon. Approximate Query Processing: Taming the TeraBytes. In Proceedings of the International Conference on Very Large Data Bases (VLDB), 2001."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304208"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/253260.253291"},{"key":"e_1_3_2_1_28_1","author":"Horvitz D. G.","year":"1952","unstructured":"D. G. Horvitz and D. J. Thompson . A generalization of sampling without replacement from a finite universe. Journal of the American statistical Association , 1952 . D. G. Horvitz and D. J. Thompson. A generalization of sampling without replacement from a finite universe. Journal of the American statistical Association, 1952.","journal-title":"Journal of the American statistical Association"},{"key":"e_1_3_2_1_29_1","volume-title":"CoRR","author":"Kamat N.","year":"2016","unstructured":"N. Kamat and A. Nandi . Perfect and maximum randomness in stratified sampling over joins . CoRR , 2016 . N. Kamat and A. Nandi. Perfect and maximum randomness in stratified sampling over joins. CoRR, 2016."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3085504.3085524"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056099"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883026"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2401603.2401626"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915235"},{"key":"e_1_3_2_1_35_1","volume-title":"Cengage Learning","author":"Lohr S.","year":"2009","unstructured":"S. Lohr . Sampling : design and analysis . Cengage Learning , 2009 . S. Lohr. Sampling: design and analysis. Cengage Learning, 2009."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056098"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","DOI":"10.1007\/b102247","volume-title":"Imprecise and Approximate Computation","author":"Natarajan S.","year":"1995","unstructured":"S. Natarajan . Imprecise and Approximate Computation . Kluwer Academic Publishers , 1995 . S. Natarajan. Imprecise and Approximate Computation. Kluwer Academic Publishers, 1995."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the International Conference on Very Large Data Bases (VLDB)","author":"Pansare N.","year":"2011","unstructured":"N. Pansare , V. R. Borkar , C. Jermaine , and T. Condie . Online aggregation for large mapreduce jobs . In Proceedings of the International Conference on Very Large Data Bases (VLDB) , 2011 . N. Pansare, V. R. Borkar, C. Jermaine, and T. Condie. Online aggregation for large mapreduce jobs. In Proceedings of the International Conference on Very Large Data Bases (VLDB), 2011."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196905"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/2777598.2777599"},{"key":"e_1_3_2_1_42_1","volume-title":"Approximate distributed joins in apache spark. CoRR, abs\/1805.05874","author":"Quoc D. L.","year":"2018","unstructured":"D. L. Quoc , I. E. Akkus , P. Bhatotia , S. Blanas , R. Chen , C. Fetzer , and T. Strufe . Approximate distributed joins in apache spark. CoRR, abs\/1805.05874 , 2018 . D. L. Quoc, I. E. Akkus, P. Bhatotia, S. Blanas, R. Chen, C. Fetzer, and T. Strufe. Approximate distributed joins in apache spark. CoRR, abs\/1805.05874, 2018."},{"key":"e_1_3_2_1_43_1","volume-title":"Privacy preserving stream analytics: The marriage of randomized response and approximate computing. CoRR, abs\/1701.05403","author":"Quoc D. L.","year":"2017","unstructured":"D. L. Quoc , M. Beck , P. Bhatotia , R. Chen , C. Fetzer , and T. Strufe . Privacy preserving stream analytics: The marriage of randomized response and approximate computing. CoRR, abs\/1701.05403 , 2017 . D. L. Quoc, M. Beck, P. Bhatotia, R. Chen, C. Fetzer, and T. Strufe. Privacy preserving stream analytics: The marriage of randomized response and approximate computing. CoRR, abs\/1701.05403, 2017."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 2017 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC)","author":"Quoc D. L.","year":"2017","unstructured":"D. L. Quoc , M. Beck , P. Bhatotia , R. Chen , C. Fetzer , and T. Strufe . PrivApprox: Privacy-Preserving Stream Analytics . In Proceedings of the 2017 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC) , 2017 . D. L. Quoc, M. Beck, P. Bhatotia, R. Chen, C. Fetzer, and T. Strufe. PrivApprox: Privacy-Preserving Stream Analytics. In Proceedings of the 2017 USENIX Conference on USENIX Annual Technical Conference (USENIX ATC), 2017."},{"key":"e_1_3_2_1_45_1","volume-title":"Approximate Stream Analytics in Apache Flink and Apache Spark Streaming. CoRR, abs\/1709.02946","author":"Quoc D. L.","year":"2017","unstructured":"D. L. Quoc , R. Chen , P. Bhatotia , C. Fetzer , V. Hilt , and T. Strufe . Approximate Stream Analytics in Apache Flink and Apache Spark Streaming. CoRR, abs\/1709.02946 , 2017 . D. L. Quoc, R. Chen, P. Bhatotia, C. Fetzer, V. Hilt, and T. Strufe. Approximate Stream Analytics in Apache Flink and Apache Spark Streaming. CoRR, abs\/1709.02946, 2017."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135989"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2899408"},{"key":"e_1_3_2_1_48_1","volume-title":"Wiley Series in Probability and Statistics","author":"Thompson S. K.","year":"2012","unstructured":"S. K. Thompson . Sampling. Wiley Series in Probability and Statistics , 2012 . S. K. Thompson. Sampling. Wiley Series in Probability and Statistics, 2012."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2972950"},{"key":"e_1_3_2_1_51_1","first-page":"373","volume-title":"In Proceedings of the 2015 International Conference on Extending Database Technology (EDBT)","author":"Tian Y.","year":"2015","unstructured":"Y. Tian , T. Zou , F. Ozcan , R. Goncalves , and H. Pirahesh . Joins for hybrid warehouses: Exploiting massive parallelism in hadoop and enterprise data warehouses . In In Proceedings of the 2015 International Conference on Extending Database Technology (EDBT) , pages 373 -- 384 , 2015 . Y. Tian, T. Zou, F. Ozcan, R. Goncalves, and H. Pirahesh. Joins for hybrid warehouses: Exploiting massive parallelism in hadoop and enterprise data warehouses. In In Proceedings of the 2015 International Conference on Extending Database Technology (EDBT), pages 373--384, 2015."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00048"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463701"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI)","author":"Zaharia M.","year":"2012","unstructured":"M. Zaharia , M. Chowdhury , T. Das , A. Dave , J. Ma , M. McCauley , M. J. Franklin , S. Shenker , and I. Stoica . Resilient Distributed Datasets: A Fault Tolerant Abstraction for In-Memory Cluster Computing . In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI) , 2012 . M. Zaharia, M. Chowdhury, T. Das, A. Dave, J. Ma, M. McCauley, M. J. Franklin, S. Shenker, and I. Stoica. Resilient Distributed Datasets: A Fault Tolerant Abstraction for In-Memory Cluster Computing. In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI), 2012."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/1855741.1855744"}],"event":{"name":"SoCC '18: ACM Symposium on Cloud Computing","location":"Carlsbad CA USA","acronym":"SoCC '18","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267809.3267834","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3267809.3267834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:30Z","timestamp":1750207470000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267809.3267834"}},"subtitle":["Approximate Distributed Joins"],"short-title":[],"issued":{"date-parts":[[2018,10,11]]},"references-count":53,"alternative-id":["10.1145\/3267809.3267834","10.1145\/3267809"],"URL":"https:\/\/doi.org\/10.1145\/3267809.3267834","relation":{},"subject":[],"published":{"date-parts":[[2018,10,11]]},"assertion":[{"value":"2018-10-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}