Patent · US Active

Neural network categorization accuracy with categorical graph neural networks

US11551039B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 28, 2020
Grant dateJan 10, 2023
Priority date
Expiry dateMar 19, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/289
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Neural network-based categorization can be improved by incorporating graph neural networks that operate on a graph representing the taxonomy of the categories into which a given input is to be categorized by the neural network based-categorization. The output of a graph neural network, operating on a graph representing the taxonomy of categories, can be combined with the output of a neural network operating upon the input to be categorized, such as through an interaction of multidimensional output data, such as a dot product of output vectors. In such a manner, information conveying the explicit relationships between categories, as defined by the taxonomy, can be incorporated into the categorization. To recapture information, incorporate new information, or reemphasize information a second neural network can also operate upon the input to be categorized, with the output of such a second neural network being merged with the output of the interaction.

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