Neural network categorization accuracy with categorical graph neural networks

A system comprising:

• a processing unit;
• and
• a computer-readable storage medium storing computer-executable instructions, which, when executed, cause the system to:
• provide a graph to a graph neural network, the graph comprising nodes corresponding to categories and edges between the nodes in accordance with relationships between the categories;
• provide, to a machine learning model, a first input that is to be categorized into one or more of the categories;
• perform an interaction involving the graph neural network and the machine learning model;
• and
• based at least on the interaction, determine a first category of the first input.

A computer-readable storage medium storing computer-executable instructions, which, when executed, cause a computing device to perform acts comprising:

• providing a graph to a graph neural network, the graph comprising nodes corresponding to categories and edges between the nodes in accordance with relationships between the categories;
• providing, to a machine learning model, a first input that is to be categorized into one or more of the categories;
• and
• determining a first category of the first input based at least on an output of the graph neural network and an output of the machine learning model.