Dimensionality reduction is a very important part in the field of face recognition. In view of the problem of the traditional dimensionality reduction methods are inconvenient to select neighbor parameter K and the “dense” characteristic of the low-rank representation coefficient matrix. We presented a method that semi-supervised discriminant analysis via weighted low-rank representation and adaptive neighbor selection (ANSWLR-SDA). First, we uses all the within-class samples to construct the within-class graph which can describe the within-class compactness, and then adaptively chooses the between-class samples to construct the between-class graph which can describe the between-class respectively. On this basis, we use a regularization term by weighted low-rank represented to maintain the global similarity structure of samples. Finally, we carry out the experiments on FERET and yale_faceb databases, and compare this method with the traditional dimensionality reduction methods and the results demonstrate that ANSWLR-SDA method is effectiveness and robust to different types of noise than other state-of-art face recognition method.