Instance Selection Method for Improving Graph-Based Semi-supervised Learning

Graph-based semi-supervised learning (GSSL) is one of the most important semi-supervised learning (SSL) paradigms. Though GSSL methods are helpful in many situations, they may hurt performance when using unlabeled data. In this paper, we propose a new GSSL method GsslIs based on instance selection in order to reduce the chances of performance degeneration. Our basic idea is that given a set of unlabeled instances, it is not the best to exploit all the unlabeled instances; instead, we should exploit the unlabeled instances which are highly possible to help improve the performance, while do not take the ones with high risk into account. Experiments on a board range of data sets show that the chance of performance degeneration of our proposal is much smaller than that of many state-of-the-art GSSL methods.