Adaptive Nonnegative Matrix Factorization Method

Non-negative matrix factorization (NMF) is useful in finding basis information of non-negative data. It is a new dimension reduction method. Currently, the multiplicative update method proposed by Lee and Seung is a simple and popular way to find the factorization. In this paper, an adaptive NMF method is proposed. The primary ideas of methods as follows: when columns are added to the data matrix, factorization results obtained through data matrix plus columns regarded as a new data matrix, and then Lee and Seung NMF method run on it. Finally, experiment results are given.