Patent · US Active

Graph neural network training methods and systems

US11227190B1 · kind B1 · utility

5Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 29, 2021
Grant dateJan 18, 2022
Priority date
Expiry dateJun 29, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/022
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus for training a graph neural network. An example method includes obtaining a complete graph; dividing the complete graph into a plurality of subgraphs; obtaining a training graph to participate in graph neural network training based on selecting at least one subgraph from the plurality of subgraphs; obtaining, based on the training graph, a node feature vector of each node in the training graph; obtaining a node fusion vector of each current node in the training graph; determining a loss function based on node labels and the node fusion vectors in the training graph; and iteratively training the graph neural network to update parameter values of the graph neural network based on optimizing the loss function.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.