Skip to content
/ FedUV Public

Reproduce of "Federated Learning of User Verification Models Without Sharing Embeddings" (FedUV) presented at ICML'21

License

Notifications You must be signed in to change notification settings

eggry/FedUV

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FedUV

Run

python main.py --dataset_root /data2/datasets/ --verbose --cuda --device 1 --normalize --comment withnormalize127 

python main.py --dataset_root /data2/datasets/ --verbose --cuda --device 0 --comment wonormalize127

python main.py --dataset_root /data2/datasets/ --verbose --cuda --device 2 --normalize --code_length 511 --message_length 67 --d_min 175 --comment withnormalize511

python main.py --dataset_root /data2/datasets/ --verbose --cuda --device 1 --code_length 511 --message_length 67 --d_min 175 --comment wonormalize511

Result

The model overfits. The metrics are shown in this Tensorboard.

About

Reproduce of "Federated Learning of User Verification Models Without Sharing Embeddings" (FedUV) presented at ICML'21

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages