Invention Grant
- Patent Title: Generating neighborhood convolutions according to relative importance
-
Application No.: US16273969Application Date: 2019-02-12
-
Publication No.: US11227014B2Publication Date: 2022-01-18
- Inventor: Jurij Leskovec , Chantat Eksombatchai , Kaifeng Chen , Ruining He , Rex Ying
- Applicant: Pinterest, Inc.
- Applicant Address: US CA San Francisco
- Assignee: Pinterest, Inc.
- Current Assignee: Pinterest, Inc.
- Current Assignee Address: US CA San Francisco
- Agency: Althorus, PLLC
- Main IPC: G06F16/901
- IPC: G06F16/901 ; G06F16/906 ; G06K9/62 ; G06F16/9536 ; G06F16/9535 ; G06N3/04 ; G06K9/68 ; G06F16/51 ; G06N20/00 ; G06F16/22 ; G06N3/08 ; G06F16/182 ; G06F16/9035 ; G06F9/38

Abstract:
Systems and methods for generating embeddings for nodes of a corpus graph are presented. More particularly, embedding information of a target node may be based on the node itself, as well as related, relevant nodes to the target node within a corpus graph. The information of various nodes among the relevant nodes to the target node can be used to weight or influence the embedding information. Disclosed systems and methods include generating neighborhood embedding information for a target node, where the neighborhood embedding information includes embedding information from neighborhood nodes of the target node's relevant neighborhood, and where certain nodes having more relevance to the target node can be weighted to influence the generation of the neighborhood embedding information over nodes having less relevance to the target node.
Public/Granted literature
- US20190286659A1 GENERATING NEIGHBORHOOD CONVOLUTIONS ACCORDING TO RELATIVE IMPORTANCE Public/Granted day:2019-09-19
Information query