search

FuChong-cyber / label-inference-attacks

Code & supplementary material of the paper Label Inference Attacks Against Federated Learning on Usenix Security 2022.
MIT License
79 stars 16 forks source link

Help about the training speed #7

Open YuanShunJie1 opened 9 months ago

YuanShunJie1 commented 9 months ago

Hello, I am trying to reproduce the results of the defense strategy against label inference attacks on 4090. However, I find that the training speed is too slow. I wonder is there something wrong?

This is the running script: python vfl_framework.py --use-mal-optim True --use-mal-optim-all False --use-mal-optim-top False -d CIFAR10 --path-dataset /Datasets/CIFAR10 --k 5 --epochs 100 --half 16 --lap-noise True --noise-scale 1e-3

FuChong-cyber commented 9 months ago

That's strange. Are you running with pytorch-cpu? This command works fine on my PC with RTX 3090 x1.

YuanShunJie1 commented 9 months ago

No, I run it with a GPU 4090.

YuanShunJie1 commented 9 months ago

Maybe I find the problem. Thanks.