Orthogonal Non-negative Matrix Factorization: a Maximum-Entropy-Principle Approach

In this paper, we introduce a new methodology to solve the orthogonal non-negative matrix factorization (ONMF) problem, where the objective is to approximate an input data matrix by the product of two non-negative matrices, the features matrix and the mixing matrix, while one of them is orthogonal. We show how the ONMF can be interpreted as a specific facility-location problem (FLP), and adapt a maximum-entropy-principle based solution for FLP to the ONMF problem. The proposed approach guarantees orthogonality of the features or the mixing matrix, while ensuring that both of the matrix factors are non-negative. Also, the features (mixing) matrix has exactly one non-zero element across each row (column), providing the maximum sparsity of the orthogonal factor. This enables a semantic interpretation of the underlying data matrix using non-overlapping features. The experiments on synthetic data and a standard microarray dataset demonstrate significant improvements in terms of sparsity and orthogonality scores of features (mixing) matrices, while achieving approximately the same or better (up to 3%) reconstruction errors.