The program consists of five linear label space transformation approaches. The base learner used in all approaches is regularized linear regression with a fixed regularization parameter. Please see the usage in demo.m .
-
Binary Relevance with Random Discarding (BR), Principal Label Space Transformation (PLST) are developed in
Farbound Tai and Hsuan-Tien Lin. Multilabel classification with principal label space transformation. Neural Computation, 24(9):2508--2542, September 2012.
-
Conditional Principal Label Space Transformation (CPLST) is developed
Yao-Nan Chen and Hsuan-Tien Lin. Feature-aware label space dimension reduction for multi-label classification. In Advances in Neural Information Processing Systems: Proceedings of the 2012 Conference (NIPS), pages 1538--1546, December 2012.
-
Feature-aware Implicit label space Encoding (FaIE) is developed in
Lin, Zijia, et al. "Multi-label Classification via Feature-aware Implicit Label Space Encoding." Proceedings of the 31st International Conference on Machine Learning (ICML-14). 2014.
-
Column Subset Selection Problem (CSSP) is developed in
Bi, Wei, and James Kwok. "Efficient multi-label classification with many labels." Proceedings of the 30th International Conference on Machine Learning (ICML-13). 2013.
Please cite the these papers if you find the program useful.
If there are any questions, please feel free to contact the corresponding author of the first two papers at
Hsuan-Tien Lin, htlin@csie.ntu.edu.tw
The corresponding author thanks his co-authors of the papers, especially Farbound Tai who contributed significantly to the initial layout of the program.