wenzhu23333/Differential-Privacy-Based-Federated-Learning
Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )
PythonGPL-3.0
Issues
- 0
RuntimeError: setStorage: sizes [1, 8, 3, 1, 1, 1034], strides [8288, 1036, 1036, 1, 1036, 1], storage offset 0, and itemsize 4 requiring a storage size of 41432 are out of bounds for storage of size 33152
#31 opened by zzk1212 - 0
每次运行都会提示Warning,如何解决?
#30 opened by sherlock-CHN - 0
- 5
关于使用dp=5时,精度没达到原本预期的问题
#23 opened by sherlock-CHN - 4
为什么每次训练出来的精度都是一样的呢
#27 opened by studyupupup - 2
作者您好
#26 opened by ltmwglobal - 3
关于计算噪声机制中 scale 值的问题
#21 opened by Red9th - 1
- 1
关于梯度加噪的问题
#22 opened by sherlock-CHN - 0
Is it pending to have a new version on LLMs?
#25 opened by wwh0411 - 2
- 5
Sensitivity caculation of different mechanism
#18 opened by Toby-Kang - 0
- 7
problem of setting
#16 opened by nekopalaa - 9
- 10
DP sensitivity calculation
#14 opened by eardic - 2
请教
#15 opened by Speed-Fiorna - 1
Hyperparameters for training cnn for cifar 10
#13 opened by Toby-Kang - 2
你好,关于本地训练回合问题
#12 opened by a-row-person - 3
- 3
Out of memory
#10 opened by key2miao - 3
- 2
想问下关于Sensitivity计算的问题
#8 opened by xiyuanyang45 - 4
- 1
- 1
您好!
#5 opened by Marziachir - 1
- 4
精度很低
#3 opened by zz978233034 - 1
- 1
请问epsilon和clip的值怎么选取呢
#1 opened by whb98