Method and device for representing nodes in network

The invention discloses a method and device for representing nodes in a network. The method comprises the steps of: obtaining a first degree value of a first node and a second degree value of a secondnode as well as a weight value of an edge between the first node and the second node in the network; determining similar information between the first node and the second node according to the firstdegree value, the second degree value and the weight value; sampling the nodes in the network on the basis of the similar information to obtain a sampling sequence; and determining a target sequence corresponding to the sampling sequence by adopting a long and short term memory model, wherein a mapping model is arranged between an input layer and a hidden layer of the long and short term memory model and the mapping model is used for learning node vectors of the nodes in the process of determining the target sequence corresponding to the sampling sequence by the long and short term memory model and optimizing the node