Adaptive Semi-Supervised Classification by Joint Global and Local Graph

Abstract

Recently, semisupervised classification methods have been widely applied in many scientific fields, among them, the graph-based methods of semisupervised classification have attracted great attention due to their effectiveness. However, most existing graph-based multi-view methods only construct a graph on each view, and cannot make full use of the abundant information provided by multi-view data. In addition, some semisupervised classification methods directly learn a fixed graph with original input data which contain noise that result in unreliable graphs. Based on these considerations, we propose a novel adaptive multi-view semisupervised classification model which construct a joint global-local graph with total views to attain the connection between each view and within each view. Our model can obtain a better consistency structure and learn the weight coefficient automatically after finite iterations. We also develop a nongreedy optimization algorithm to solve our objective function. In our model, we studied the effect of the global structure on the overall classification performance, and the experiments verified the theoretical derivation. We also studied the effect of label ratio on classification accuracy in different algorithms. The experimental results show that the classification accuracy of our algorithm is higher than other existing algorithms in the range of moderate label ratio so that it has great advantages in practical applications. When the global graph is added, the model still has good performance in terms of running time and convergence rate. The comprehensive experiments on different real-world datasets show the effectiveness of the proposed approach and demonstrate the advantage over other methods.