Patent · US Active

Graph neural networks for datasets with heterophily

US12175366B2 · kind B2 · utility

0Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 23, 2021
Grant dateDec 24, 2024
Priority date
Expiry dateOct 26, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/02
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques are provided for training graph neural networks with heterophily datasets and generating predictions for such datasets with heterophily. A computing device receives a dataset including a graph data structure and processes the dataset using a graph neural network. The graph neural network defines prior belief vectors respectively corresponding to nodes of the graph data structure, executes a compatibility-guided propagation from the set of prior belief vectors and using a compatibility matrix. The graph neural network predicts predicting a class label for a node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within a neighborhood of the node. The computing device outputs the graph data structure where it is usable by a software tool for modifying an operation of a computing environment.

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