Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD FOR TRAINING LOCAL NEURAL NETWORK MODEL FOR FEDERATED LEARNING
Document Type and Number:
WIPO Patent Application WO/2024/058465
Kind Code:
A1
Abstract:
A task to be achieved in the present disclosure is to train a local neural network model based on federated learning in consideration of a heterogeneous environment providing different training data. A training method for training a local neural network model based on federated learning, the method being performed by at least one computing device, according to an embodiment of the present disclosure for achieving the task described above, may comprises the steps of: calculating the difference between a global neural network model and the local neural network model; determining additional regularization for training the local neural network model, on the basis of the calculated difference; and training the local neural network model on the basis of a loss function including the determined additional regularization.

Inventors:
KIM YEACHAN (KR)
SHIN BONGGUN (KR)
Application Number:
PCT/KR2023/012843
Publication Date:
March 21, 2024
Filing Date:
August 30, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
DEARGEN INC (KR)
International Classes:
G06N3/098; G06N3/045; G06N3/0985
Foreign References:
KR20220103247A2022-07-22
KR20220097201A2022-07-07
KR20220067926A2022-05-25
KR20210121914A2021-10-08
Other References:
EK SANNARA; PORTET FRANCOIS; LALANDA PHILIPPE; VEGA GERMAN: "Artifact: A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison", 2021 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS WORKSHOPS AND OTHER AFFILIATED EVENTS (PERCOM WORKSHOPS), IEEE, 22 March 2021 (2021-03-22), pages 448 - 449, XP033917138, DOI: 10.1109/PerComWorkshops51409.2021.9431080
Attorney, Agent or Firm:
LEE, Dae Ho et al. (KR)
Download PDF: