Multi-Classification using One-versus-One Deep Learning Strategy with Joint Probability Estimates
This work addresses a specific bottleneck in multi-class classification for machine learning practitioners, offering an incremental improvement over existing methods.
The paper tackled the problem of low classification accuracy in One-versus-One multi-classification models due to voting mechanisms, proposing a novel model with joint probability estimates under deep learning, which achieved generally higher accuracy than state-of-the-art models in numerical experiments.
The One-versus-One (OvO) strategy is an approach of multi-classification models which focuses on training binary classifiers between each pair of classes. While the OvO strategy takes advantage of balanced training data, the classification accuracy is usually hindered by the voting mechanism to combine all binary classifiers. In this paper, a novel OvO multi-classification model incorporating a joint probability measure is proposed under the deep learning framework. In the proposed model, a two-stage algorithm is developed to estimate the class probability from the pairwise binary classifiers. Given the binary classifiers, the pairwise probability estimate is calibrated by a distance measure on the separating feature hyperplane. From that, the class probability of the subject is estimated by solving a joint probability-based distance minimization problem. Numerical experiments in different applications show that the proposed model achieves generally higher classification accuracy than other state-of-the-art models.