BriefGPT.xyz
Apr, 2022
部分模型个性化的联邦学习
Federated Learning with Partial Model Personalization
HTML
PDF
Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi...
TL;DR
研究内容为探讨联邦学习算法中，共享参数和个性化参数同时或交替更新，以及在非凸有限参与的情况下的收敛性分析，实验证明部分个性化模型效果同等于全模型个性化效果，且交替更新算法在一定程度上优于同时更新算法。
Abstract
We consider two
federated learning
algorithms for training partially
personalized models
, where the shared and personal parameters are updated either simultaneously or alternately on the devices. Both algorithms
→