{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T01:51:19Z","timestamp":1761789079610,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642374494"},{"type":"electronic","value":"9783642374500"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-37450-0_26","type":"book-chapter","created":{"date-parts":[[2013,4,17]],"date-time":"2013-04-17T05:41:52Z","timestamp":1366177312000},"page":"339-353","source":"Crossref","is-referenced-by-count":2,"title":["Computing the Split Points for Learning Decision Tree in MapReduce"],"prefix":"10.1007","author":[{"given":"Mingdong","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Kou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiezheng","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"26_CR1","unstructured":"Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., Gruber, R.E.: Bigtable: A Distributed Storage System for Structured Data. In: Proc. of OSDI, pp. 205\u2013218 (2006)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Cooper, B.F., Ramakrishnan, R., Srivastava, U., Silberstein, A., Bohannon, P., Jacobsen, H., Puz, N., Weaver, D., Yerneni, R.: Pnuts: Yahoo!\u2019s Hosted Data Serving Platform. In: Proc. of VLDB, pp. 1277\u20131288 (2008)","DOI":"10.14778\/1454159.1454167"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"DeCandia, G., Hastorun, D., Jampani, M., Kakulapati, G., Lakshman, A., Pilchin, A., Sivasubramanian, S., Vosshall, P., Vogels, W.: Dynamo: Amazons Highly Available Key-value Store. In: Proc. of SOSP, pp. 205\u2013220 (2007)","DOI":"10.1145\/1323293.1294281"},{"key":"26_CR4","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified Data Processing on Large Clusters. In: Proc. of OSDI, pp. 137\u2013150 (2004)"},{"key":"26_CR5","unstructured":"Hadoop Project, http:\/\/hadoop.apache.org\/"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Laptev, N., Zeng, K., Zaniolo, C.: Early Accurate Results for Advanced Analytics on MapReduce. In: Proc. of VLDB, pp. 1028\u20131039 (2012)","DOI":"10.14778\/2336664.2336675"},{"issue":"9","key":"26_CR7","first-page":"575","volume":"4","author":"M.Y. Eltabakh","year":"2011","unstructured":"Eltabakh, M.Y., Tian, Y., \u00d6zcan, F., Gemulla, R., Krettek, A., McPherson, J.: CoHadoop: Flexible Data Placement and Its Exploitation in Hadoop. PVLDB\u00a04(9), 575\u2013585 (2011)","journal-title":"PVLDB"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Gerth, J., Talbot, J., Elmeleegy, K., Sears, R.: Online Aggregation and Continuous Query Support in MapReduce. In: Proc. of SIGMOD, pp. 1115\u20131118 (2010)","DOI":"10.1145\/1807167.1807295"},{"issue":"6","key":"26_CR9","first-page":"586","volume":"5","author":"I. Elghandour","year":"2012","unstructured":"Elghandour, I., Aboulnaga, A.: ReStore: Reusing Results of MapReduce Jobs. PVLDB\u00a05(6), 586\u2013597 (2012)","journal-title":"PVLDB"},{"issue":"2","key":"26_CR10","first-page":"1414","volume":"2","author":"A. Gates","year":"2009","unstructured":"Gates, A., Natkovich, O., Chopra, S., Kamath, P., Narayanamurthy, S., Olston, C., Reed, B., Srinivasan, S., Srivastava, U.: Building a HighLevel Dataflow System on Top of MapReduce: the Pig Experience. PVLDB\u00a02(2), 1414\u20131425 (2009)","journal-title":"PVLDB"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig Latin: A Not-So-Foreign Language for Data Processing. In: Proc. of SIGMOD, pp. 1099\u20131110 (2008)","DOI":"10.1145\/1376616.1376726"},{"issue":"2","key":"26_CR12","first-page":"1626","volume":"2","author":"A. Thusoo","year":"2009","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive: A Warehousing Solution Over a Map-Reduce Framework. PVLDB\u00a02(2), 1626\u20131629 (2009)","journal-title":"PVLDB"},{"key":"26_CR13","unstructured":"Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth (1984)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Gehrke, J., Ganti, V., Ramakrishnan, R., Loh, W.-Y.: BOAT-Optimistic Decision Tree Construction. In: Proc. of SIGMOD, pp. 169\u2013180 (1999)","DOI":"10.1145\/304181.304197"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Mehta, M., Agrawal, R., Rissanen, J.: SLIQ: A fast scalable classifier for datamining. In: Proc. of EDBT, pp. 18\u201332 (1996)","DOI":"10.1007\/BFb0014141"},{"key":"26_CR16","unstructured":"Gehrke, J., Ramakrishnan, R., Ganti, V.: RainForest - A Framework for Fast Decision Tree Construction of Large Datasets. In: Proc. of VLDB, pp. 416\u2013427 (1998)"},{"key":"26_CR17","unstructured":"Shafer, J., Agrawal, R., Mehta, M.: SPRINT: A Scalable Parallel Classifier for Data Mining. In: Proc. of VLDB, pp. 544\u2013555 (1996)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Domingos, P., Hulten, G.: Mining High-Speed Data Streams. In: Proc. of KDD, pp. 71\u201380 (2000)","DOI":"10.1145\/347090.347107"},{"issue":"2","key":"26_CR19","first-page":"1426","volume":"2","author":"B. Panda","year":"2009","unstructured":"Panda, B., Herbach, J., Basu, S., Bayardo, R.: PLANET: Massively Parallel Learning of Tree Ensembles with MapReduce. PVLDB\u00a02(2), 1426\u20131437 (2009)","journal-title":"PVLDB"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Ye, J., Chow, J., Chen, J., Zheng, Z.: Stochastic Gradient Boosted Distributed Decision Trees. In: Proc. of CIKM, pp. 2061\u20132064 (2009)","DOI":"10.1145\/1645953.1646301"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Hall, L., Chawla, N., Bowyer, K.W.: Decision tree learning on Very Large Data Dets. In: Proc. of SMC, vol.\u00a03, pp. 2579\u20132584 (1998)","DOI":"10.1109\/ICSMC.1998.725047"},{"issue":"2","key":"26_CR22","first-page":"109","volume":"5","author":"J. Jestes","year":"2011","unstructured":"Jestes, J., Yi, K., Li, F.: Building Wavelet Histograms on Large Data in MapReduce. PVLDB\u00a05(2), 109\u2013120 (2011)","journal-title":"PVLDB"},{"key":"26_CR23","unstructured":"Agrawal, R., Ghosh, S., Imielinski, T., Iyer, B., Swami, A.: An Interval Classifier for Database Mining Appliation. In: Proc. of VLDB, pp. 560\u2013573 (1992)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Jin, R., Agrawal, G.: Communication and Memory Efficient Parallel Decision Tree Construction. In: Proc. of SDM, pp. 119\u2013129 (2003)","DOI":"10.1137\/1.9781611972733.11"},{"key":"26_CR25","first-page":"849","volume":"11","author":"Y. Ben-Haim","year":"2010","unstructured":"Ben-Haim, Y., Tom-Tov, E.: A Streaming Parallel Decision Tree Algorithm. Journal of Machine Learning Research (JMLR)\u00a011, 849\u2013872 (2010)","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"26_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/978-3-642-16248-0_89","volume-title":"Rough Set and Knowledge Technology","author":"Q. He","year":"2010","unstructured":"He, Q., Zhuang, F., Li, J., Shi, Z.: Parallel implementation of classification algorithms based on mapReduce. In: Yu, J., Greco, S., Lingras, P., Wang, G., Skowron, A. (eds.) RSKT 2010. LNCS, vol.\u00a06401, pp. 655\u2013662. Springer, Heidelberg (2010)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Yi, K., Zhang, Q.: Optimal Tracking of Distributed Heavy Hitters and Quantiles. In: Proc. of PODS, pp. 167\u2013174 (2009)","DOI":"10.1145\/1559795.1559820"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, L., Yi, K., Liu, Y.: Sampling Based Algorithms for Quantile Computation in Sensor Networks. In: Proc. of SIGMOD, pp. 745\u2013756 (2011)","DOI":"10.1145\/1989323.1989401"},{"key":"26_CR29","unstructured":"Sina Weibo, http:\/\/www.weibo.com\/"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-37450-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:13:06Z","timestamp":1745989986000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-37450-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642374494","9783642374500"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-37450-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}