Outlying subspace searching algorithm based on power graph
基于幂图的离群子空间搜索算法*

By analyzing the current outlier searching algorithms and the existing problems, proposed an outlying subspace searching algorithm based on power graph. This algorithm mainly discussed the reason for generating outliers and could identify outlier subspaces of a single object. Next, it classified outliers based on these outlier subspaces. Lastly, by pruning on the basis of the expansion of the power graph, reducing storage and computation, algorithm performance had been greatly improved. The algorithm is illustrated by an example and the experimental results show the feasibility and efficiency.