{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:32:38Z","timestamp":1790152358582,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,4]],"date-time":"2017-08-04T00:00:00Z","timestamp":1501804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-13-2-0020"],"award-info":[{"award-number":["FA8750-13-2-0020"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-1451512"],"award-info":[{"award-number":["NSF-1451512"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,4]]},"DOI":"10.1145\/3097983.3098079","type":"proceedings-article","created":{"date-parts":[[2017,8,4]],"date-time":"2017-08-04T18:35:54Z","timestamp":1501871754000},"page":"255-264","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["A Hierarchical Algorithm for Extreme Clustering"],"prefix":"10.1145","author":[{"given":"Ari","family":"Kobren","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Monath","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akshay","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"McCallum","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"M. Ackerman and S. Dasgupta 2014. Incremental clustering: The case for extra clusters Advances in Neural Information Processing Systems.  M. Ackerman and S. Dasgupta 2014. Incremental clustering: The case for extra clusters Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2133803.2184450"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012722442-8\/50016-1"},{"key":"e_1_3_2_2_4_1","volume-title":"Fastex: Hash clustering with exponential families. Advances in Neural Information Processing Systems.","author":"Ahmed A.","year":"2012","unstructured":"A. Ahmed , S. Ravi , A. J. Smola , and S. M. Narayanamurthy . 2012 . Fastex: Hash clustering with exponential families. Advances in Neural Information Processing Systems. A. Ahmed, S. Ravi, A. J. Smola, and S. M. Narayanamurthy. 2012. Fastex: Hash clustering with exponential families. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_5_1","volume-title":"Symposium on Discrete Algorithms.","author":"Arthur D.","year":"2007","unstructured":"D. Arthur and S. Vassilvitskii 2007 . k-means: The advantages of careful seeding . In Symposium on Discrete Algorithms. D. Arthur and S. Vassilvitskii 2007. k-means: The advantages of careful seeding. In Symposium on Discrete Algorithms."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509947"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"M. Balcan A. Blum and S. Vempala 2008. A discriminative framework for clustering via similarity functions ACM Symposium on Theory of Computing.  M. Balcan A. Blum and S. Vempala 2008. A discriminative framework for clustering via similarity functions ACM Symposium on Theory of Computing.","DOI":"10.1145\/1374376.1374474"},{"key":"e_1_3_2_2_8_1","unstructured":"B. Betancourt G. Zanella J. W. Miller H. Wallach A. Zaidi and R. C. Steorts. 2016. Flexible models for microclustering with application to entity resolution Advances in Neural Information Processing Systems.  B. Betancourt G. Zanella J. W. Miller H. Wallach A. Zaidi and R. C. Steorts. 2016. Flexible models for microclustering with application to entity resolution Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143857"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"C. Blundell Y. W. Teh and K. A. Heller 2011. Discovering non-binary hierarchical structures with Bayesian rose trees Mixture Estimation and Applications.  C. Blundell Y. W. Teh and K. A. Heller 2011. Discovering non-binary hierarchical structures with Bayesian rose trees Mixture Estimation and Applications.","DOI":"10.1002\/9781119995678.ch8"},{"key":"e_1_3_2_2_11_1","unstructured":"L. Bottou and Y. Bengio 1995. Convergence properties of the k-means algorithms. Advances in Neural Information Processing Systems.  L. Bottou and Y. Bengio 1995. Convergence properties of the k-means algorithms. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_12_1","unstructured":"P. F. Brown P. V. Desouza R. L. Mercer V. J. D. Pietra and J. C. Lai 1992. Class-based n-gram models of natural language. In Computational Linguistics.  P. F. Brown P. V. Desouza R. L. Mercer V. J. D. Pietra and J. C. Lai 1992. Class-based n-gram models of natural language. In Computational Linguistics."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"M. Charikar C. Chekuri T. Feder and R. Motwani. 1997. Incremental clustering and dynamic information retrieval Symposium on Theory of Computing.  M. Charikar C. Chekuri T. Feder and R. Motwani. 1997. Incremental clustering and dynamic information retrieval Symposium on Theory of Computing.","DOI":"10.1145\/258533.258657"},{"key":"e_1_3_2_2_14_1","volume":"201","author":"Choromanska A. E.","unstructured":"A. E. Choromanska and J. Langford 201 5. Logarithmic time online multiclass prediction. In Advances in Neural Information Processing Systems. A. E. Choromanska and J. Langford 2015. Logarithmic time online multiclass prediction. In Advances in Neural Information Processing Systems.","journal-title":"J. Langford"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.70.066111"},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning.","author":"H.","year":"2017","unstructured":"H. Daume III, N. Karampatziakis , J. Langford , and P. Mineiro 2017 . Logarithmic time one-against-some . In International Conference on Machine Learning. H. Daume III, N. Karampatziakis, J. Langford, and P. Mineiro 2017. Logarithmic time one-against-some. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_17_1","volume-title":"Fei-Fei","author":"Deng J.","year":"2009","unstructured":"J. Deng , W. Dong , R. Socher , L. Li , K. Li , and L. Fei-Fei 2009 . Imagenet : A large-scale hierarchical image database Computer Vision and Pattern Recognition . J. Deng, W. Dong, R. Socher, L. Li, K. Li, and L. Fei-Fei 2009. Imagenet: A large-scale hierarchical image database Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"M. B. Eisen P. T. Spellman P. O. Brown and D. Botstein 1998. Cluster analysis and display of genome-wide expression patterns National Academy of Sciences.  M. B. Eisen P. T. Spellman P. O. Brown and D. Botstein 1998. Cluster analysis and display of genome-wide expression patterns National Academy of Sciences.","DOI":"10.1073\/pnas.95.25.14863"},{"key":"e_1_3_2_2_19_1","unstructured":"M. Ester H.-P. Kriegel J. Sander X. Xu and others 1996. A density-based algorithm for discovering clusters in large spatial databases with noise International Conference on Knowledge Discovery and Data Mining.  M. Ester H.-P. Kriegel J. Sander X. Xu and others 1996. A density-based algorithm for discovering clusters in large spatial databases with noise International Conference on Knowledge Discovery and Data Mining."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40450-4_41"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000042993.50813.60"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73750-6"},{"key":"e_1_3_2_2_23_1","volume-title":"The NIST 2014 speaker recognition i-vector machine learning challenge Odyssey.","author":"Greenberg C. S.","unstructured":"C. S. Greenberg , D. Bans\u00e9 , G. R. Doddington , D. Garcia-Romero , J. J. Godfrey , T. Kinnunen , A. F. Martin , A. McCree , M. Przybocki , and D. A. Reynolds . 2014 . The NIST 2014 speaker recognition i-vector machine learning challenge Odyssey. C. S. Greenberg, D. Bans\u00e9, G. R. Doddington, D. Garcia-Romero, J. J. Godfrey, T. Kinnunen, A. F. Martin, A. McCree, M. Przybocki, and D. A. Reynolds. 2014. The NIST 2014 speaker recognition i-vector machine learning challenge Odyssey."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"A. Guttman. 1984. R-trees: a dynamic index structure for spatial searching International Conference on Management of Data.  A. Guttman. 1984. R-trees: a dynamic index structure for spatial searching International Conference on Management of Data.","DOI":"10.1145\/602259.602266"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102389"},{"key":"e_1_3_2_2_26_1","unstructured":"M. D. Hoffman D. M. Blei C. Wang and J. W. Paisley. 2013. Stochastic variational inference. In Journal of Machine Learning Research.  M. D. Hoffman D. M. Blei C. Wang and J. W. Paisley. 2013. Stochastic variational inference. In Journal of Machine Learning Research."},{"key":"e_1_3_2_2_27_1","unstructured":"A. Krishnamurthy S. Balakrishnan M. Xu and A. Singh. 2012. Efficient active algorithms for hierarchical clustering International Conference on Machine Learning.  A. Krishnamurthy S. Balakrishnan M. Xu and A. Singh. 2012. Efficient active algorithms for hierarchical clustering International Conference on Machine Learning."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974317.7"},{"key":"e_1_3_2_2_29_1","unstructured":"M. Lichman. 2013. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml  M. Lichman. 2013. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"e_1_3_2_2_31_1","unstructured":"L. O'callaghan N. Mishra A. Meyerson S. Guha and R. Motwani 2002. Streaming-data algorithms for high-quality clustering International Conference on Data Engineering.  L. O'callaghan N. Mishra A. Meyerson S. Guha and R. Motwani 2002. Streaming-data algorithms for high-quality clustering International Conference on Data Engineering."},{"key":"e_1_3_2_2_32_1","volume-title":"Five Balltree Construction Algorithms","author":"Omohundro S. M.","unstructured":"S. M. Omohundro . 1989. Five Balltree Construction Algorithms . International Computer Science Institute Berkeley . S. M. Omohundro. 1989. Five Balltree Construction Algorithms. International Computer Science Institute Berkeley."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"R. Ostrovsky Y. Rabani L. J. Schulman and C. Swamy. 2006. The effectiveness of Lloyd-type methods for the k-means problem Foundations of Computer Science.  R. Ostrovsky Y. Rabani L. J. Schulman and C. Swamy. 2006. The effectiveness of Lloyd-type methods for the k-means problem Foundations of Computer Science.","DOI":"10.1109\/FOCS.2006.75"},{"key":"e_1_3_2_2_34_1","volume-title":"Duchesnay","author":"Pedregosa F.","year":"2011","unstructured":"F. Pedregosa , G. Varoquaux , A. Gramfort , V. Michel , B. Thirion , O. Grisel , M. Blondel , P. Prettenhofer , R. Weiss , V. Dubourg , J. Vanderplas , A. Passos , D. Cournapeau , M. Brucher , M. Perrot , and E. Duchesnay 2011 . Scikit-learn : Machine learning in Python. In Journal of Machine Learning Research . F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay 2011. Scikit-learn: Machine learning in Python. In Journal of Machine Learning Research."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr1079"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"e_1_3_2_2_38_1","unstructured":"R. Sedgewick. 1988. Algorithms. Pearson Education India.  R. Sedgewick. 1988. Algorithms. Pearson Education India."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"C. Szegedy V. Vanhoucke S. Ioffe J. Shlens and Z. Wojna 2016. Rethinking the inception architecture for computer vision Computer Vision and Pattern Recognition.  C. Szegedy V. Vanhoucke S. Ioffe J. Shlens and Z. Wojna 2016. Rethinking the inception architecture for computer vision Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_2_40_1","volume":"200","author":"Widyantoro D. H.","unstructured":"D. H. Widyantoro , T. R. Ioerger , and J. Yen 200 2. An incremental approach to building a cluster hierarchy International Conference on Data Mining. D. H. Widyantoro, T. R. Ioerger, and J. Yen 2002. An incremental approach to building a cluster hierarchy International Conference on Data Mining.","journal-title":"J. Yen"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233324"}],"event":{"name":"KDD '17: The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"Halifax NS Canada","acronym":"KDD '17","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3098079","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097983.3098079","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097983.3098079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:30:26Z","timestamp":1750217426000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3098079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,4]]},"references-count":41,"alternative-id":["10.1145\/3097983.3098079","10.1145\/3097983"],"URL":"https:\/\/doi.org\/10.1145\/3097983.3098079","relation":{},"subject":[],"published":{"date-parts":[[2017,8,4]]},"assertion":[{"value":"2017-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}