The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Dec. 02, 2025

Filed:

Aug. 11, 2021
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Baoxu Shi, San Jose, CA (US);

Qi He, San Jose, CA (US);

Jaewon Yang, Campbell, CA (US);

Sufeng Niu, Fremont, CA (US);

Minji Yoon, Pittsburgh, PA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2023.01); G06F 18/20 (2023.01); G06F 18/21 (2023.01); G06F 18/211 (2023.01); G06F 18/2431 (2023.01);
U.S. Cl.
CPC ...
G06F 18/29 (2023.01); G06F 18/211 (2023.01); G06F 18/217 (2023.01); G06F 18/2431 (2023.01); G06N 3/08 (2013.01);
Abstract

Techniques for implementing a performance-adaptive sampling strategy towards fast and accurate graph neural networks are provided. In one technique, a graph that comprises multiple nodes and edges connecting the nodes is stored. An embedding for each node is initialized, as well as a sampling policy for sampling neighbors of nodes. One or more machine learning techniques are used to train a graph neural network and learn embeddings for the nodes. Using the one or more machine learning techniques comprises, for each node: (1) selecting, based on the sampling policy, a set of neighbors of the node; (2) based on the graph neural network and embeddings for the node and the set of neighbors, computing a performance loss; and (3) based on a gradient of the performance loss, modifying the sampling policy.


Find Patent Forward Citations

Loading…