This paper proposes a novel graph-based transductive learning algorithm based on manifold regularization.First,the manifold regularization was introduced to probabilistic discriminant model for semi-supervised classification task.And then a variation of the expectation maximization(EM) algorithm was derived to solve the optimization problem,which leads to an iterative algorithm.Although our method is developed in probabilistic framework,there is no need to make assumption about the specific form of data distribution.Besides,the crucial updating formula has closed form.This method was evaluated for text categorization on two standard datasets,20 news group and Reuters-21578.Experiments show that our approach outperforms the state-of-the-art graph-based transductive learning methods. This paper proposes a novel graph-based transductive learning algorithm based on manifold regularization. First, the manifold regularization was introduced to probabilistic discriminant model for semi-supervised classification task. And then a variation of the expectation maximization (EM) algorithm was derived to solve the optimization problem, which leads to an iterative algorithm .Although our method is developed in a probabilistic framework, there is no need to make assumption about the specific form of data distribution.Besides, the crucial updating formula has closed form. This method was evaluated as text categorization on two standard datasets, 20 news group and Reuters-21578. Experiments that that approach approachperform the state-of-the-art graph-based transductive learning methods.