Machine learning is widely used in various applications such as data mining, computer vision, and bioinformatics owing to the explosion of available data. However, in practice, many data have some missing attributes. The graphic theory serves as a powerful tool for modeling and analyzing many such practical problems, such as networks of communication and data organization. This paper focuses on semi-supervised learning algorithms based on the graph theory, aiming at establishing robust models in the input space with a very limited number of training samples. The use of such algorithm in multiple data mining applications is also discussed.
展开▼