Hierarchical Maximum Margin Learning for Multi-Class Classification
This work addresses multi-class classification problems with many classes, offering an incremental improvement in accuracy for real-world large-scale applications.
The paper tackles the challenge of designing accurate and efficient classifiers for multi-class classification with many classes by proposing a novel method to learn a binary hierarchical tree structure, which improves accuracy over benchmarks on most datasets while maintaining comparable efficiency.
Due to myriads of classes, designing accurate and efficient classifiers becomes very challenging for multi-class classification. Recent research has shown that class structure learning can greatly facilitate multi-class learning. In this paper, we propose a novel method to learn the class structure for multi-class classification problems. The class structure is assumed to be a binary hierarchical tree. To learn such a tree, we propose a maximum separating margin method to determine the child nodes of any internal node. The proposed method ensures that two classgroups represented by any two sibling nodes are most separable. In the experiments, we evaluate the accuracy and efficiency of the proposed method over other multi-class classification methods on real world large-scale problems. The results show that the proposed method outperforms benchmark methods in terms of accuracy for most datasets and performs comparably with other class structure learning methods in terms of efficiency for all datasets.