Binary Relevance Multi-label Conformal Predictor

详细信息    查看全文

• 关键词：Multi ; label ; Conformal prediction ; Confidence measures
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9653
• 期：1
• 页码：90-104
• 全文大小：698 KB
• 参考文献：1.Vovk, V., Gammerman, A., Shafer, G.: Algorithmic Learning in a Random World. Springer, New York (2005)MATH
  2.Gammerman, A., Vovk, V., Vapnik, V.: Learning by transduction. In: Uncertainty in Artificial Intelligence, pp. 148–155. Morgan Kaufmann (1998)
  3.Balasubramanian, V.N., Ho, S.-S., Vovk, V. (eds.): Conformal Prediction for Reliable Machine Learning. Morgan Kaufmann, Boston (2014). doi:10.​1016/​B978-0-12-398537-8.​00014-6 . http://​www.​sciencedirect.​com/​science/​article/​pii/​B978012398537800​0146 . ISBN 978-0-12-398537-8MATH
  4.Saunders, C., Gammerman, A., Vovk, V.: Transduction with confidence and credibility. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence, vol. 2, pp. 722–726. Morgan Kaufmann, Los Altos (1999)
  5.Papadopoulos, H., Vovk, V., Gammerman, A.: Regression conformal prediction with nearest neighbours. J. Artif. Intell. Res. 40, 815–840 (2011)MathSciNet MATH
  6.Devetyarov, D., Nouretdinov, I.: Prediction with confidence based on a random forest classifier. In: Papadopoulos, H., Andreou, A.S., Bramer, M. (eds.) AIAI 2010. IFIP AICT, vol. 339, pp. 37–44. Springer, Heidelberg (2010). doi:10.​1007/​978-3-642-16239-8_​8 CrossRef
  7.Bellotti, T., Luo, Z., Gammerman, A., Van Delft, F.W., Saha, V.: Qualified predictions for microarray and proteomics pattern diagnostics with confidence machines. Int. J. Neural Syst. 15(4), 247–258 (2005)CrossRef
  8.Gammerman, A., Nouretdinov, I., Burford, B., Chervonenkis, A., Vovk, V., Luo, Z.: Clinical mass spectrometry proteomic diagnosis by conformal predictors. Stat. Appl. Genet. Mol. Biol. 7(2) (2008). http://​dx.​doi.​org/​10.​2202/​1544-6115.​1385
  9.Papadopoulos, H., Gammerman, A., Vovk, V.: Confidence predictions for the diagnosis of acute abdominal pain. In: Iliadis, Maglogiann, Tsoumakasis, Vlahavas, Bramer, (eds.) Artificial Intelligence Applications and Innovations III. IFIP, vol. 296, pp. 175–184. Springer, US (2009)CrossRef
  10.Papadopoulos, H., Gammerman, A., Vovk, V.: Reliable diagnosis of acute abdominal pain with conformal prediction. Int. J. Eng. Intell. Syst. Electr. Eng. Commun. 17(2–3), 127–137 (2009). ISSN 1472–8915
  11.Balasubramanian, V.N., Chakraborty, S., Panchanathan, S.: Conformal predictions for information fusion. Annals Math. Artif. Intell. 74(1–2), 45–65 (2015). doi:10.​1007/​s10472-013-9392-4 . ISSN 1012–2443MathSciNet CrossRef MATH
  12.Yang, M., Nouretdunov, I., Luo, Z., Gammerman, A.: Feature selection by conformal predictor. In: Iliadis, L., Maglogiannis, I., Papadopoulos, H. (eds.) EANN/AIAI 2011, Part II. IFIP AICT, vol. 364, pp. 439–448. Springer, Heidelberg (2011). doi:10.​1007/​978-3-642-23960-1_​51 . ISBN 978-3-642-23959-5CrossRef
  13.Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehouse. Min. 1–13, 2007 (2007)
  14.Wieczorkowska, A., Synak, P., Raś, Z.W.: Multi-label classification of emotions in music. In: Kłopotek, M.A., Wierzchoń, S.T., Trojanowski, K. (eds.) Intelligent Information Processing and Web Mining. Advances in Soft Computing, vol. 35, pp. 307–315. Springer, Heidelberg (2006). doi:10.​1007/​3-540-33521-8_​30 . ISBN 978-3-540-33520-7CrossRef
  15.Papadopoulos, H.: A cross-conformal predictor for multi-label classification. In: Iliadis, L., Maglogiannis, I., Papadopoulos, H., Sioutas, S., Makris, C. (eds.) Artificial Intelligence Applications and Innovations. IFIP AICT, vol. 437, pp. 241–250. Springer, Heidelberg (2014). doi:10.​1007/​978-3-662-44722-2_​26 . ISBN 978-3-662-44721-5
  16.Wang, H., Liu, X., Lv, B., Yang, F., Hong, Y.: Reliable multi-label learning via conformal predictor, random forest for syndrome differentiation of chronic fatigue in traditional chinese medicine. PLoS ONE 9(6), e99565 (2014)CrossRef
  17.Wang, H., Liu, X., Nouretdinov, I., Luo, Z.: A comparison of three implementations of multi-label conformal prediction. In: Gammerman, A., Vovk, V., Papadopoulos, H. (eds.) Statistical Learning and Data Sciences. LNCS, vol. 9047, pp. 241–250. Springer, Switzerland (2015). doi:10.​1007/​978-3-319-17091-6_​19 . ISBN 978-3-319-17091-6CrossRef
  18.Papadopoulos, H., Vovk, V., Gammerman, A.: Qualified predictions for large data sets in the case of pattern recognition. In: Proceedings of the International Conference on Machine Learning and Applications (ICMLA 2002), pp. 159–163. CSREA Press (2002)
  19.Elisseeff, A., Weston, J.: A kernel method for multi-labelled classification. In: Advances in Neural Information Processing Systems 14, pp. 681–687. MIT Press (2001)
  
• 作者单位：Antonis Lambrou (17)
  Harris Papadopoulos (17) (18)
  
  17. Computer Learning Research Centre Royal Holloway, University of London, London, UK
  18. Computer Science and Engineering Department, Frederick University, Nicosia, Cyprus
  
• 丛书名：Conformal and Probabilistic Prediction with Applications
• ISBN：978-3-319-33395-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9653

文摘

The Conformal Prediction (CP) framework can be used for obtaining reliable confidence measures in Machine Learning applications. The confidence measures are guaranteed to be valid under the assumption that the data used are identically and independently distributed (i.i.d.). In this work, we extend the CP framework for multi-label classification, where an instance can belong to multiple classes in parallel. Applications include image tagging, document classification, and music classification. We give an overview of the Conformal Prediction framework, and we describe the developed Binary Relevance Multi-Label Conformal Predictor (BR-MLCP). We propose a new measure of confidence using Chebyshev’s inequality together with the hamming loss metric. Our experimental results demonstrate the reliability of our new confidence measure.