Invention Grant
- Patent Title: Bayesian graph convolutional neural networks
-
Application No.: US16697124Application Date: 2019-11-26
-
Publication No.: US11531886B2Publication Date: 2022-12-20
- Inventor: Yingxue Zhang , Soumyasundar Pal , Mark Coates , Deniz Ustebay
- Applicant: Yingxue Zhang , Soumyasundar Pal , Mark Coates , Deniz Ustebay
- Applicant Address: CA Montreal; CA Montreal; CA Montreal; CA Westmount
- Assignee: Yingxue Zhang,Soumyasundar Pal,Mark Coates,Deniz Ustebay
- Current Assignee: Yingxue Zhang,Soumyasundar Pal,Mark Coates,Deniz Ustebay
- Current Assignee Address: CA Montreal; CA Montreal; CA Montreal; CA Westmount
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06K9/62

Abstract:
Method and system for predicting labels for nodes in an observed graph, including deriving a plurality of random graph realizations of the observed graph; learning a predictive function using the random graph realizations; predicting label probabilities for nodes of the random graph realizations using the learned predictive function; and averaging the predicted label probabilities to predict labels for the nodes of the observed graph.
Public/Granted literature
- US20210158149A1 BAYESIAN GRAPH CONVOLUTIONAL NEURAL NETWORKS Public/Granted day:2021-05-27
Information query