Method and System for Graph-to-graph Prediction Based on Recurrent Neural Network
AssigneeYangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China
InventorGuan WANG
Life of this patent
Estimating the term…
Loading patent…
AssigneeYangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China
InventorGuan WANG
Estimating the term…
The present disclosure discloses a method and system for graph-to-graph prediction based on recurrent neural networks. The method includes: representing a graph structure as a sequence; based on the sequentialization representation of the graph structure, constructing a deep neural network model for graph-to-graph prediction, wherein both input and output of the deep neural network model are graph structures; the deep neural network model includes an Encoder and a Decoder, wherein, in the Encoder, employing encNodeRNN and encEdgeRNN in combination to encode an input graph, and the Decoder decodes based on an encoding vector obtained from the Encoder, thereby obtaining a corresponding predicted graph and realizing the graph-to-graph prediction.
A graph-to-graph prediction method, comprising:
Dependencies are inferred from the claim text.