Title:
IMPROVED DISTRIBUTED TRAINING OF GRAPH-EMBEDDING NEURAL NETWORKS
Document Type and Number:
WIPO Patent Application WO/2022/133725
Kind Code:
A1
Abstract:
A method for distributed training of a graph-embedding neural network, performed at a first server, comprises: computing, based on a first input data sample, first model data and first embedding data of a first graph neural network, the first graph neural network corresponding to a first set of nodes of a graph that are visible to the first server; sharing the first model data and the first embedding data with a second server; receiving second embedding data from a third server, the second embedding data comprising embedding data of a second graph neural network corresponding to a second set of nodes of the graph that are invisible to the first server; and computing second model data of the first graph neural network based on a second input data sample and the embedding data of the second graph neural network.
Inventors:
WANG LAN (CN)
YU LEI (CN)
JIANG LI (CN)
YU LEI (CN)
JIANG LI (CN)
Application Number:
PCT/CN2020/138290
Publication Date:
June 30, 2022
Filing Date:
December 22, 2020
Export Citation:
Assignee:
ORANGE (FR)
WANG LAN (CN)
YU LEI (CN)
JIANG LI (CN)
WANG LAN (CN)
YU LEI (CN)
JIANG LI (CN)
International Classes:
G06N3/04
Foreign References:
CN110782044A | 2020-02-11 | |||
US20190156214A1 | 2019-05-23 | |||
US20200104688A1 | 2020-04-02 | |||
CN112085172A | 2020-12-15 | |||
CN110348573A | 2019-10-18 | |||
CN110751275A | 2020-02-04 |
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF: