Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND SYSTEM FOR RELATION LEARNING BY MULTI-HOP ATTENTION GRAPH NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2022/063151
Kind Code:
A1
Abstract:
System and method for completing knowledge graph. The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to: provide an incomplete knowledge graph comprising a plurality of nodes and a plurality of edges, each of the edges connecting two of the plurality of nodes; calculate an attention matrix of the incomplete knowledge graph based on one-hop attention between any two of the plurality of the nodes that are connected by one of the plurality of the edges; calculate multi-head diffusion attention for any two of the plurality of nodes from the attention matrix; obtain updated embedding of the incomplete knowledge graph using the multi-head diffusion attention; and update the incomplete knowledge graph to obtain updated knowledge graph based on the updated embedding.

Inventors:
WANG GUANGTAO (US)
YING ZHITAO (US)
HUANG JING (US)
LESKOVEC JURIJ (US)
Application Number:
PCT/CN2021/119792
Publication Date:
March 31, 2022
Filing Date:
September 23, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING WODONG TIANJUN INFORMATION TECHNOLOGY CO LTD (CN)
JD COM AMERICAN TECH CORP (US)
UNIV LELAND STANFORD JUNIOR (US)
International Classes:
G06N5/02
Foreign References:
US20200104729A12020-04-02
CN111259142A2020-06-09
US20200226472A12020-07-16
JP2020087127A2020-06-04
US20200193245A12020-06-18
CN110196928A2019-09-03
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: