Error-correcting Semi-supervised Learning with Extended Mode Filter on Graphs

抄録

We present a robust semi-supervised method using the extended mode filter for learning with partially-labeled training data including label errors. The mode filter was originally developed for smoothing images contaminated with impulsive noises and usually needs iterative solution methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension by UCI benchmark data and UMIST Face Database