Extreme multi-label learning or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves 2L possible label sets when the label dimension L is very large e.g. in millions for Wikipedia labels. This paper is motivated to better explore the label space by build- ing and modeling an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems includ- ing multi-label classification, however it has not been sufficiently studied in this extreme but practi- cal case, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classifi- cation. Our method harvests the ideas of non-linear embedding and modeling label space with graph priors at the same time. Extensive experiments on public datasets for XML show that our method per- form competitively against state-of-the-art result.