Abstract
A common way of solving a multi-class classification problem is to decompose it into a collection of simpler two-class problems. One major disadvantage is that with such a binary decomposition scheme it may be difficult to represent subtle between-class differences in many-class classification problems due to limited choices of binary-value partitions. To overcome this challenge, we propose a new decomposition method called N-ary decomposition that decomposes the original multi-class problem into a set of simpler multi-class subproblems. We theoretically show that the proposed N-ary decomposition could be unified into the framework of error correcting output codes and give the generalization error bound of an N-ary decomposition for multi-class classification. Extensive experimental results demonstrate the state-of-the-art performance of our approach.
Original language | English |
---|---|
Pages (from-to) | 809-830 |
Number of pages | 22 |
Journal | Machine Learning |
Volume | 108 |
Issue number | 5 |
DOIs | |
Publication status | Published - 2019 May 15 |
Keywords
- Ensemble learning
- Multi-class classification
- N-ary ECOC
ASJC Scopus subject areas
- Software
- Artificial Intelligence