A Cross-Conformal Predictor for Multi-label Classification
作者： Harris Papadopoulos
DOI: 10.1007/978-3-662-44722-2_26
关键词: Task (project management) 、 Single class 、 Computer science 、 Multi-label classification 、 Machine learning 、 Conformal map 、 Artificial intelligence 、 Instance-based learning
摘要: Unlike the typical classification setting where each instance is associated with a single class, in multi-label learning multiple classes simultaneously. Therefore task this to predict subset of which belongs. This work examines application recently developed framework called Conformal Prediction (CP) setting. CP complements predictions machine algorithms reliable measures confidence. As result proposed approach instead just predicting most likely for new unseen instance, also indicates likelihood predicted being correct. additional information especially valuable overall uncertainty extremely high.
springer.com
sci-hub.st 参考文章(12)
Ioannis Katakis, O Maimon, Grigorios Tsoumakas, Ioannis Vlahavas, Mining Multi-label Data Data Mining and Knowledge Discovery Handbook. pp. 667- 685 ,(2009) , 10.1007/978-0-387-09823-4_34
Alexander Gammerman, Vladimir Vovk, Harris Papadopoulos, Qualified Prediction for Large Data Sets in the Case of Pattern Recognition. international conference on machine learning and applications. pp. 159- 163 ,(2002)
Harris Papadopoulos, Kostas Proedrou, Volodya Vovk, Alex Gammerman, Inductive Confidence Machines for Regression Lecture Notes in Computer Science. pp. 345- 356 ,(2002) , 10.1007/3-540-36755-1_29
Alex Gammerman, Vladimir Vovk, Glenn Shafer, Algorithmic Learning in a Random World ,(2007)
Min-Ling Zhang, José M Peña, Victor Robles, None, Feature selection for multi-label naive Bayes classification Information Sciences. ,vol. 179, pp. 3218- 3229 ,(2009) , 10.1016/J.INS.2009.06.010
Min-Ling Zhang, Ml-rbf: RBF Neural Networks for Multi-Label Learning Neural Processing Letters. ,vol. 29, pp. 61- 74 ,(2009) , 10.1007/S11063-009-9095-3
Vladimir Vovk, Cross-conformal predictors Annals of Mathematics and Artificial Intelligence. ,vol. 74, pp. 9- 28 ,(2015) , 10.1007/S10472-013-9368-4
Min-Ling Zhang, Zhi-Hua Zhou, ML-KNN: A lazy learning approach to multi-label learning Pattern Recognition. ,vol. 40, pp. 2038- 2048 ,(2007) , 10.1016/J.PATCOG.2006.12.019
André Elisseeff, Jason Weston, A kernel method for multi-labelled classification neural information processing systems. ,vol. 14, pp. 681- 687 ,(2001)
Min-Ling Zhang, Zhi-Hua Zhou, Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization IEEE Transactions on Knowledge and Data Engineering. ,vol. 18, pp. 1338- 1351 ,(2006) , 10.1109/TKDE.2006.162