ICMLJul, 2020
边缘联邦学习的编码计算
Coded Computing for Federated Learning at the Edge
Saurav Prakash, Sagar Dhakal, Mustafa Akdeniz, A. Salman Avestimehr, Nageen Himayat
TL;DRCodedFedL extends CFL to distributed non-linear regression and classification problems with multioutput labels by exploiting distributed kernel embedding using random Fourier features that transforms the training task into distributed linear regression, providing an analytical solution for load allocation and significant performance gains over benchmark datasets using practical network parameters.