List your company
ResearchFormerly WizWand

Training Efficiency on ResNet architecture

22.06Latency (s)FedAvg
20.517230.931141.34551.7589Sep 27, 2024
Updated 8mo ago

Evaluation results

MethodLinks
FedAvgBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0922.061
FedDynBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0934.031.54
SCAFFOLDBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0936.011.63
A-FedPDBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0937.611.7
FedSAMBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0939.211.77
FedSpeedBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0956.12.54
A-FedPDSAMBackbone=ResNet, Iterations per round=100, Hardware=NVIDIA GeForce RTX 2080 Ti, Platform=Pytorch 2.0.1, Cuda version=11.72024.0960.632.74