Different neural network architectures at the parties

IBM / federated-learning-lib

A library for federated learning (a distributed machine learning process) in an enterprise environment.

Other

493 stars 134 forks source link

Different neural network architectures at the parties #126

Open CriZ-sd opened 1 year ago

CriZ-sd commented 1 year ago

Hi, does IBM FL support to use different Neural Network architecture at each party(for example using 4 parties and each party trains a different local Neural Network architecture)? If yes, then which fusion algorithm (aggregation protocol) is better for this purpose ?

Yi-Zoey commented 1 year ago

Hi @CriZ-sd you can check and see if PFNM works for your use case? Also, see the paper for PFNM here for more information.