Label reconstruction algorithm for multi-label classification

被引：0

作者：

Liu, Lu ^{[1
]}

Jing, Ling ^{[1
]}

机构：

[1] College of Science, China Agriculture University, Beijing

来源：

Journal of Information and Computational Science | 2015年 / 12卷 / 12期

关键词：

Label propagation; Label reconstruction; Multi-label classification;

D O I：

10.12733/jics20106373

中图分类号：

学科分类号：

摘要：

Multi-label classification problem is one of the most significant classification problems in real life. Each instance is correlated to a set of labels. The target is to design a classifier so that when instances are input we can obtain their labels. In this paper, a multi-label learning approach named Label Reconstruction Algorithm (ML-LR) is put forward, which is derived from the traditional Label Propagation Algorithm for binary classification. In detail, for each new instance, its k nearest neighborhoods are found out at first. Then, the neighborhoods which have been identified are applied to reconstruct the instance. After that, the reconstruction coefficients are used to calculate the label set of the new instance. The experimental consequences on real-world Yeast data and Scene data show the effectiveness of ML-LR. Copyright © 2015 Binary Information Press.

引用

页码：4811 / 4819

页数：8

共 13 条

[1]

Lewis D.D., Et al., RCV1: A new benchmark collection for text categorization research, Journal of Machine Learning Research, pp. 361-397, (2004)

[2]

Snoek C., Et al., The challenge problem for automated detection of 101 semantic concepts in multimedia, Proceedings of the 14th annual ACM international conference on Multimedia, ACM, pp. 421-430, (2006)

[3]

Tsoumakas G., Katakis I., Vlahavas I., Random k-labelsets for multilabel classification, IEEE Transactions on Knowledge and Data Engineering, 23, 7, pp. 1079-1089, (2011)

[4]

Fuernkranz J., Et al., Multilabel classification via calibrated label ranking, Machine Learning, 73, 2, pp. 133-153, (2008)

[5]

Boutell M.R., Et al., Learning multi-label scene classification, Pattern Recognition, 37, 9, pp. 1757-1771, (2004)

[6]

Shen X.P., Et al., Multi-label machine learning and its application to semantic scene classification, Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE), pp. 188-199, (2004)

[7]

Huellermeier E., Et al., Label ranking by learning pairwise preferences, Artificial Intelligence, 172, 16-17, pp. 1897-1916, (2008)

[8]

Schapire R.E., Singer Y., BoosTexter: A boosting-based system for text categorization, Machine Learning, 39, 2-3, pp. 135-168, (2000)

[9]

Wang F., Zhang C., Label propagation through linear neighborhoods, IEEE Transactions on Knowledge and Data Engineering, 20, 1, pp. 55-67, (2008)

[10]

Szummer M., Jaakkola T., Partially labeled classification with Markov random walks, Advances in Neural Information Processing Systems, pp. 945-952, (2002)

← 1 2 →