ADAPTIVE AGGREGATION FOR FEDERATED LEARNING

Systems and Methods for adaptive aggregation in a federated learning model. An aggregation server (121) sends global model weights to all chosen collaborators (131) for initialization. Each collaborator (131) updates the model weights for certain epochs and then sends the updated model weights back...

Full description

Saved in:
Bibliographic Details
Main Authors YOO, Youngjin, ULLASKRISHNAN, Poikavila, PATEL, Pragneshkumar, PALADINI, Gianluca, COMANICIU, Dorin, GIBSON, Eli
Format Patent
LanguageEnglish
French
German
Published 05.04.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Systems and Methods for adaptive aggregation in a federated learning model. An aggregation server (121) sends global model weights to all chosen collaborators (131) for initialization. Each collaborator (131) updates the model weights for certain epochs and then sends the updated model weights back to the aggregation server (121). The aggregation server (121) adaptively aggregates the updated model weights using at least a computed model divergence value and sends the aggregated model weight to collaborators (131).
Bibliography:Application Number: EP20220197895