Multi-model Adaptation Method of Possibilistic Clustering Assumption

Abstract

Graph based semi-supervised learning (GSSL) has been attracting more and more attention with its intui-tiveness and good learning performance in the machine learning community. However, it is found that existing graph based semi-supervised learning method has the problem of poor robustness and sensitivity to noise and abnor-mal data by analysis. In addition, the premise for the GSSL to have good performance is that the training data and test data are independently identically distribution (IID), which leads to some limitations in practical applications. In order to solve above problems, this paper proposes a novel clustering method based on structure risk minimization model, called a multi-model adaptation method of possibilistic clustering assumption (MA-PCA), and effectively minimizes the influence from the noise and abnormal instances based on different data distributions in some reproduced kernel Hilbert space. Its main ideas are as follows: the negative impact of noise and abnormal data on the method is reduced through fuzzy entropy; considering the effective multi-model adaptive learning of training data and test data in the same distribution and different distributions, it can also obtain good performance by rela-xing the constraint of IID between training data and test data; the algorithm implementation and convergence the-orem are given. A large number of experiments and in-depth analysis on multiple real visual datasets show that the proposed method has superior or comparable robustness and generalization performance.

Keywords

• graph based semi-supervised learning (gssl); multi-model adaptation; possibilistic clustering; fuzzy entropy