-
Following @rabbanitw's comment, extending our federated averaging methods to support [FedProx](https://arxiv.org/pdf/1812.06127) would greatly improve Disco's robustness to client heterogeneity (data …
-
Hello, I noticed that the code only compares FedAVG , FedProx and Oracle, but I don't see FedCIL included.
-
## Describe the bug
Currently FedAvg does not perform well even in homogeneous settings for models with batchnorms such as resnet18. The accuracy over epochs curve is highly erratic and does not reac…
-
Thank you for your amazing work and open-souring the implementation.
I wonder why in the Table 1 of your paper, the results of
- pFedPrompt
- PromptFL+FT
- PromptFL+FedPer
- PromptFL+FedAMP
…
-
Could you clarify how do you calculate the avg_gradient that is given as input in the pggd file? I could not find the script that imports this file.
https://github.com/litian96/FedProx/blob/master/fl…
-
We need to clearly separate OpenFL samples (which would just show how to integrate OpenFL and various use-cases) and tutorials or lifehachks (how to add your custom aggregation function/play with assi…
-
Hello,I want to ask for a help:
In the "main_fedml_image_segmentation. py" file of the fedcv module, "SegmentationTrainer. py" and "SegmentationAggregator. py" under the "image_segmentation/trai…
-
I remember in Li's paper the proximal term is defined to be the quadratic norm-2 of the (w - w^t), but in the client.py the proximal term is implemented as the sum of the norm-2s.
Screenshot on the…
-
According to Algorithm 2, there is a parameter gamma in the input which measures how much local
computation is performed to solve the local subproblem on device k at the t-th round.
![image](https:/…
-
# FedSM
* **Title:** Closing the Generalization Gap of Cross-Silo Federated Medical Image Segmentation
* **Venue:** CVPR 2022
* **Link to paper:** https://openaccess.thecvf.com/content/CVPR2022/html/…