Network embedding method based on attribute and structure deep fusion and model thereof

The invention discloses a network embedding method based on attribute and structure deep fusion. The network embedding method comprises the following steps: S1, obtaining node attribute characteristics of a reconstructed coding layer; S2, obtaining a node attribute information sequence with node attribute characteristics; and S3, translating the node attribute information sequence into a node identity sequence to obtain node embedded vector representation capable of retaining the network structure and the node attribute information of the original network. The invention further discloses a network embedding model based on attribute and structure deep fusion. The network embedding model comprises a multi-modal attribute sensing module, an attribute embedding layer and a multi-hop structuresensing module. The multi-mode attribute sensing module is connected with the multi-hop structure sensing module through the attribute embedding layer. According to the network embedding method basedon attribute and structure