公开(公告)号：US20240386266A1

公开(公告)日：2024-11-21

申请号：US18666088

申请日：2024-05-16

Applicant: NEC Laboratories America, Inc.

Inventor： Jonathan Warrell ,  Eric Cosatto ,  Renqiang Min ,  Tianci Song

IPC: G06N3/08

Abstract: A method for graph analysis includes identifying trainable control parameters of a graph refinement function. Sample graph refinements of an input graph are generated, using control parameters sampled from a variational distribution. Graph refinement control parameters associated with a sample graph refinement that has a highest performance score are selected when used to train a graph neural network. Graph analysis is performed on the input graph using the selected graph refinement parameters to produce a refined graph on new test samples. An action is performed responsive to the graph analysis.