The FAST algorithm working in two steps. In the first step, features are divided into clusters by using graph-theoretic clustering methods. In the second step, the most delegate feature that is powerfully related to goal classes is selected from each cluster to form a subset of features. Features in different cluster are relatively independent, the clustering-based strategy of FAST has a high likelihood of producing a subset of useful and independent features. To ensure the efficiency of FAST, the authors adopt the efficient minimum-spanning tree clustering method. The efficiency and success of the FAST algorithm are evaluate through an experiential study.