Network embedding is a very important task to represent the high-dimensional network in a low-dimensional vector space,which aims to capture and preserve the network structure.Most existing network embedding methods are based on shallow models.However,the actual network structure is so complicated that the shallow model can not obtain the high-dimensional nonlinear features of the network well.The recently proposed unsupervised deep learning model of network representation learning ignores the labels information.To overcome these problems,in this paper,we propose an effective network embedding method of Structural Labeled Locally Deep Nonlinear Embedding(SLLDNE).SLLDNE is designed to obtain highly nonlinear features through utilizing deep neural network while preserving the label information of the nodes by using SVM classifier as a supervised component to improve the ability of discriminations.Moreover,we exploit linear reconstruction of neighborhood nodes to enable the model to get more structural information.The experimental results of vertex classification on two real-world network datasets demonstrate that SLLDNE outperforms the other state-of-the-art methods.