{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:14:50Z","timestamp":1750220090503,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1452425"],"award-info":[{"award-number":["1452425"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["NETCOM"],"award-info":[{"award-number":["NETCOM"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539076","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"4530-4540","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Sparx: Distributed Outlier Detection at Scale"],"prefix":"10.1145","author":[{"given":"Sean","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varun","family":"Ursekar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leman","family":"Akoglu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(03)00025-4"},{"volume-title":"Outlier analysis","author":"Aggarwal Charu C","key":"e_1_3_2_2_2_1","unstructured":"Charu C Aggarwal. 2017. Outlier analysis. Springer."},{"key":"e_1_3_2_2_3_1","volume-title":"KDD Workshop on ADF. 1--7.","author":"Anandakrishnan Archana","year":"2018","unstructured":"Archana Anandakrishnan, Senthil Kumar, Alexander Statnikov, Tanveer Faruquie, and Di Xu. 2018. Anomaly detection in finance. In KDD Workshop on ADF. 1--7."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15277-1_32"},{"key":"e_1_3_2_2_5_1","volume-title":"Distributed strategies for mining outliers in large data sets. TKDE 25, 7","author":"Angiulli Fabrizio","year":"2012","unstructured":"Fabrizio Angiulli, Stefano Basta, Stefano Lodi, and Claudio Sartori. 2012. Distributed strategies for mining outliers in large data sets. TKDE 25, 7 (2012)."},{"key":"e_1_3_2_2_6_1","unstructured":"Apache Software Foundation. [n.d.]. Hadoop. https:\/\/hadoop.apache.org"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Kanishka Bhaduri Bryan L Matthews and Chris R Giannella. 2011. Algorithms for speeding up distance-based outlier detection. In KDD. 859--867.","DOI":"10.1145\/2020408.2020554"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Markus M Breunig Hans-Peter Kriegel Raymond T Ng and J\u00f6rg Sander. 2000. LOF: identifying density-based local outliers. In SIGMOD. 93--104.","DOI":"10.1145\/335191.335388"},{"key":"e_1_3_2_2_9_1","volume-title":"DBSCOUT: A Density-based Method for Scalable Outlier Detection in Very Large Datasets. In ICDE. 37--48.","author":"Corain Matteo","year":"2021","unstructured":"Matteo Corain, Paolo Garza, and Abolfazl Asudeh. 2021. DBSCOUT: A Density-based Method for Scalable Outlier Detection in Very Large Datasets. In ICDE. 37--48."},{"key":"e_1_3_2_2_10_1","article-title":"An improved data stream summary: the count-min sketch and its applications","volume":"55","author":"Cormode Graham","year":"2005","unstructured":"Graham Cormode and Shan Muthukrishnan. 2005. An improved data stream summary: the count-min sketch and its applications. J. of Alg. 55, 1 (2005).","journal-title":"J. of Alg."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_2_12_1","volume-title":"A meta-analysis of the anomaly detection problem. arXiv preprint arXiv:1503.01158","author":"Emmott Andrew","year":"2015","unstructured":"Andrew Emmott, Shubhomoy Das, Thomas Dietterich, Alan Fern, and Weng-Keen Wong. 2015. A meta-analysis of the anomaly detection problem. arXiv preprint arXiv:1503.01158 (2015)."},{"key":"e_1_3_2_2_13_1","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"96","author":"Ester Martin","year":"1996","unstructured":"Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et al . 1996. A density-based algorithm for discovering clusters in large spatial databases with noise.. In KDD, Vol. 96. 226--231.","journal-title":"KDD"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Piotr Indyk and Rajeev Motwani. 1998. Approximate nearest neighbors: towards removing the curse of dimensionality. In STOC. 604--613.","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_2_16_1","volume-title":"Kai Ming Ting, and Zhi-Hua Zhou","author":"Liu Fei Tony","year":"2008","unstructured":"Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. 2008. Isolation forest. In ICDM. IEEE, 413--422."},{"volume-title":"Parallel algorithms for distance-based and density-based outliers","author":"Lozano Elio","key":"e_1_3_2_2_17_1","unstructured":"Elio Lozano and Edgar Acufia. 2005. Parallel algorithms for distance-based and density-based outliers. In ICDM. IEEE, 4--pp."},{"volume-title":"Distributed anomaly detection using autoencoder neural networks in WSN for IoT","author":"Luo Tie","key":"e_1_3_2_2_18_1","unstructured":"Tie Luo and Sai G Nagarajan. 2018. Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In ICC. IEEE, 1--6."},{"key":"e_1_3_2_2_19_1","volume-title":"Voelker","author":"Ma Justin","year":"2009","unstructured":"Justin Ma, Lawrence K. Saul, Stefan Savage, and Geoffrey M. Voelker. 2009. Identifying suspicious URLs: an application of large-scale online learning. In ICML. ACM, 681--688."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Emaad Manzoor Hemank Lamba and Leman Akoglu. 2018. xStream: Outlier detection in feature-evolving data streams. In KDD. 1963--1972.","DOI":"10.1145\/3219819.3220107"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220022"},{"key":"e_1_3_2_2_22_1","volume-title":"Human readable network troubleshooting based on anomaly detection and feature scoring. arXiv preprint arXiv:2108.11807","author":"Navarro Jose M","year":"2021","unstructured":"Jose M Navarro, Alexis Huet, and Dario Rossi. 2021. Human readable network troubleshooting based on anomaly detection and feature scoring. arXiv preprint arXiv:2108.11807 (2021)."},{"volume-title":"Parallel processing for distance-based outlier detection on a multi-core CPU","author":"Oku Junki","key":"e_1_3_2_2_23_1","unstructured":"Junki Oku, Keiichi Tamura, and Hajime Kitakami. 2014. Parallel processing for distance-based outlier detection on a multi-core CPU. In IWCIA. IEEE, 65--70."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/959060.959074"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2215319"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3441453","article-title":"Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Data","volume":"15","author":"Steinbuss Georg","year":"2021","unstructured":"Georg Steinbuss and Klemens B\u00f6hm. 2021. Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Data. ACM TKDD 15, 4 (2021), 1--20.","journal-title":"ACM TKDD"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2017.07.353"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1177\/1550147718814471"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5586-4"},{"volume-title":"Robust distributed anomaly detection using optimal weighted one-class random forests","author":"Tsou Yu-Lin","key":"e_1_3_2_2_30_1","unstructured":"Yu-Lin Tsou, Hong-Min Chu, Cong Li, and Shao-Wen Yang. 2018. Robust distributed anomaly detection using optimal weighted one-class random forests. In ICDM. IEEE, 1272--1277."},{"key":"e_1_3_2_2_31_1","volume-title":"Anomaly detection for large span bridges during operational phase using structural health monitoring data. Smart Mater. and Struc. 29, 4","author":"Xu Xiang","year":"2020","unstructured":"Xiang Xu, Yuan Ren, Qiao Huang, Zi-Y Fan, Zhao-J Tong, Wei-J Chang, and Bin Liu. 2020. Anomaly detection for large span bridges during operational phase using structural health monitoring data. Smart Mater. and Struc. 29, 4 (2020)."},{"key":"e_1_3_2_2_32_1","unstructured":"Yizhou Yan Lei Cao Caitlin Kulhman and Elke Rundensteiner. 2017. Distributed local outlier detection in big data. In KDD. 1225--1234."},{"volume-title":"BigData","author":"Yan Yizhou","key":"e_1_3_2_2_33_1","unstructured":"Yizhou Yan, Lei Cao, and Elke A Rundensteiner. 2017. Distributed Top-N local outlier detection in big data. In BigData. IEEE, 827--836."},{"key":"e_1_3_2_2_34_1","volume-title":"2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud).","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets. In 2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11161"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Washington DC USA","acronym":"KDD '22"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539076","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539076","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:50Z","timestamp":1750183790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":35,"alternative-id":["10.1145\/3534678.3539076","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539076","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}