{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:56:21Z","timestamp":1770335781492,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2004,8,22]],"date-time":"2004-08-22T00:00:00Z","timestamp":1093132800000},"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":[[2004,8,22]]},"DOI":"10.1145\/1014052.1014062","type":"proceedings-article","created":{"date-parts":[[2004,10,7]],"date-time":"2004-10-07T17:39:48Z","timestamp":1097170788000},"page":"59-68","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":457,"title":["A probabilistic framework for semi-supervised clustering"],"prefix":"10.1145","author":[{"given":"Sugato","family":"Basu","sequence":"first","affiliation":[{"name":"University of Texas at Austin, Austin, TX"}]},{"given":"Mikhail","family":"Bilenko","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, TX"}]},{"given":"Raymond J.","family":"Mooney","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, TX"}]}],"member":"320","published-online":{"date-parts":[[2004,8,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Modern Information Retrieval","author":"Baeza-Yates R.","year":"1999","unstructured":"R. Baeza-Yates and B. Ribeiro-Neto . Modern Information Retrieval . ACM Press , New York , 1999 . R. Baeza-Yates and B. Ribeiro-Neto. Modern Information Retrieval. ACM Press, New York, 1999."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956757"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.22"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/645413.652189"},{"key":"e_1_3_2_1_5_1","first-page":"11","volume-title":"Proceedings of 20th International Conference on Machine Learning (ICML-03)","author":"Bar-Hillel A.","year":"2003","unstructured":"A. Bar-Hillel , T. Hertz , N. Shental , and D. Weinshall . Learning distance functions using equivalence relations . In Proceedings of 20th International Conference on Machine Learning (ICML-03) , pages 11 -- 18 , 2003 . A. Bar-Hillel, T. Hertz, N. Shental, and D. Weinshall. Learning distance functions using equivalence relations. In Proceedings of 20th International Conference on Machine Learning (ICML-03), pages 11--18, 2003."},{"key":"e_1_3_2_1_6_1","first-page":"19","volume-title":"Proceedings of 19th International Conference on Machine Learning (ICML-02)","author":"Basu S.","year":"2002","unstructured":"S. Basu , A. Banerjee , and R. J. Mooney . Semi-supervised clustering by seeding . In Proceedings of 19th International Conference on Machine Learning (ICML-02) , pages 19 -- 26 , 2002 . S. Basu, A. Banerjee, and R. J. Mooney. Semi-supervised clustering by seeding. In Proceedings of 19th International Conference on Machine Learning (ICML-02), pages 19--26, 2002."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.31"},{"key":"e_1_3_2_1_8_1","first-page":"42","volume-title":"Proceedings of the ICML-2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining","author":"Basu S.","year":"2003","unstructured":"S. Basu , M. Bilenko , and R. J. Mooney . Comparing and unifying search-based and similarity-based approaches to semi-supervised clustering . In Proceedings of the ICML-2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining , pages 42 -- 49 , 2003 . S. Basu, M. Bilenko, and R. J. Mooney. Comparing and unifying search-based and similarity-based approaches to semi-supervised clustering. In Proceedings of the ICML-2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining, pages 42--49, 2003."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1986.tb01412.x"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956759"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/794191.794708"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/129837"},{"key":"e_1_3_2_1_15_1","first-page":"809","volume-title":"Artificial Neural Networks in Engineering (ANNIE-99)","author":"Demiriz A.","year":"1999","unstructured":"A. Demiriz , K. P. Bennett , and M. J. Embrechts . Semi-supervised clustering using genetic algorithms . In Artificial Neural Networks in Engineering (ANNIE-99) , pages 809 -- 814 , 1999 . A. Demiriz, K. P. Bennett, and M. J. Embrechts. Semi-supervised clustering using genetic algorithms. In Artificial Neural Networks in Engineering (ANNIE-99), pages 809--814, 1999."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/951949.952094"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007612920971"},{"key":"e_1_3_2_1_19_1","volume-title":"IBM","author":"Dom B. E.","year":"2001","unstructured":"B. E. Dom . An information-theoretic external cluster-validity measure. Research Report RJ 10219 , IBM , 2001 . B. E. Dom. An information-theoretic external cluster-validity measure. Research Report RJ 10219, IBM, 2001."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.95.25.14863"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"e_1_3_2_1_22_1","volume-title":"Markov fields on finite graphs and lattices. Unpublished manuscript","author":"Hammersley J. M.","year":"1971","unstructured":"J. M. Hammersley and P. Clifford . Markov fields on finite graphs and lattices. Unpublished manuscript , 1971 . J. M. Hammersley and P. Clifford. Markov fields on finite graphs and lattices. Unpublished manuscript, 1971."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.10.2.180"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/645528.657646"},{"key":"e_1_3_2_1_25_1","first-page":"561","volume-title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-03)","author":"Kamvar S. D.","year":"2003","unstructured":"S. D. Kamvar , D. Klein , and C. D. Manning . Spectral learning . In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-03) , pages 561 -- 566 , 2003 . S. D. Kamvar, D. Klein, and C. D. Manning. Spectral learning. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-03), pages 561--566, 2003."},{"key":"e_1_3_2_1_26_1","first-page":"282","volume-title":"Proceedings of 13th Conference on Uncertainty in Artificial Intelligence (UAI-97)","author":"Kearns M.","year":"1997","unstructured":"M. Kearns , Y. Mansour , and A. Y. Ng . An information-theoretic analysis of hard and soft assignment methods for clustering . In Proceedings of 13th Conference on Uncertainty in Artificial Intelligence (UAI-97) , pages 282 -- 293 , 1997 . M. Kearns, Y. Mansour, and A. Y. Ng. An information-theoretic analysis of hard and soft assignment methods for clustering. In Proceedings of 13th Conference on Uncertainty in Artificial Intelligence (UAI-97), pages 282--293, 1997."},{"key":"e_1_3_2_1_27_1","first-page":"307","volume-title":"Proceedings of the The Nineteenth International Conference on Machine Learning (ICML-02)","author":"Klein D.","year":"2002","unstructured":"D. Klein , S. D. Kamvar , and C. Manning . From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering . In Proceedings of the The Nineteenth International Conference on Machine Learning (ICML-02) , pages 307 -- 314 , 2002 . D. Klein, S. D. Kamvar, and C. Manning. From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering. In Proceedings of the The Nineteenth International Conference on Machine Learning (ICML-02), pages 307--314, 2002."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/795665.796512"},{"key":"e_1_3_2_1_29_1","first-page":"281","volume-title":"Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability","author":"MacQueen J.","year":"1967","unstructured":"J. MacQueen . Some methods for classification and analysis of multivariate observations . In Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability , pages 281 -- 297 , 1967 . J. MacQueen. Some methods for classification and analysis of multivariate observations. In Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, pages 281--297, 1967."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.220399497"},{"key":"e_1_3_2_1_31_1","volume-title":"Directional Statistics","author":"Mardia K. V.","year":"2000","unstructured":"K. V. Mardia and P. Jupp . Directional Statistics . John Wiley and Sons Ltd ., 2 nd edition, 2000 . K. V. Mardia and P. Jupp. Directional Statistics. John Wiley and Sons Ltd., 2nd edition, 2000.","edition":"2"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/308574.308679"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007692713085"},{"key":"e_1_3_2_1_34_1","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann","author":"Pearl J.","year":"1988","unstructured":"J. Pearl . Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann , San Mateo ,CA, 1988 . J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo,CA, 1988."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/981574.981598"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg1037"},{"key":"e_1_3_2_1_37_1","first-page":"58","volume-title":"AAAI 2000 Workshop on Artificial Intelligence for Web Search","author":"Strehl A.","year":"2000","unstructured":"A. Strehl , J. Ghosh , and R. Mooney . Impact of similarity measures on web-page clustering . In AAAI 2000 Workshop on Artificial Intelligence for Web Search , pages 58 -- 64 , July 2000 . A. Strehl, J. Ghosh, and R. Mooney. Impact of similarity measures on web-page clustering. In AAAI 2000 Workshop on Artificial Intelligence for Web Search, pages 58--64, July 2000."},{"key":"e_1_3_2_1_38_1","first-page":"577","volume-title":"Proceedings of 18th International Conference on Machine Learning (ICML-01)","author":"Wagstaff K.","year":"2001","unstructured":"K. Wagstaff , C. Cardie , S. Rogers , and S. Schroedl . Constrained K-Means clustering with background knowledge . In Proceedings of 18th International Conference on Machine Learning (ICML-01) , pages 577 -- 584 , 2001 . K. Wagstaff, C. Cardie, S. Rogers, and S. Schroedl. Constrained K-Means clustering with background knowledge. In Proceedings of 18th International Conference on Machine Learning (ICML-01), pages 577--584, 2001."},{"key":"e_1_3_2_1_39_1","first-page":"505","volume-title":"Advances in Neural Information Processing Systems 15","author":"Xing E. P.","year":"2003","unstructured":"E. P. Xing , A. Y. Ng , M. I. Jordan , and S. Russell . Distance metric learning, with application to clustering with side-information . In Advances in Neural Information Processing Systems 15 , pages 505 -- 512 , Cambridge, MA , 2003 . MIT Press . E. P. Xing, A. Y. Ng, M. I. Jordan, and S. Russell. Distance metric learning, with application to clustering with side-information. In Advances in Neural Information Processing Systems 15, pages 505--512, Cambridge, MA, 2003. MIT Press."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.906424"}],"event":{"name":"KDD04: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"Seattle WA USA","acronym":"KDD04","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1014062","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1014052.1014062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:31:30Z","timestamp":1750264290000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1014062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,8,22]]},"references-count":39,"alternative-id":["10.1145\/1014052.1014062","10.1145\/1014052"],"URL":"https:\/\/doi.org\/10.1145\/1014052.1014062","relation":{},"subject":[],"published":{"date-parts":[[2004,8,22]]},"assertion":[{"value":"2004-08-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}