-
I use this framework to reproduce some algorithms which are helpful to accelerate convergence in iid and non-iid data distribution setting, such as FedAdp, Fedatt, FedProx, all these algorithms are in…
xujli updated
2 years ago
-
In GitLab by @ybouilla on Sep 27, 2022, 18:42
_Merges feature/364-integrating-scaffold-from-poc -> develop_
This MR contains SCAFFOLD implementation for pytorch only.
/!\ ATTENTION: we should have a…
-
Hello authors,
I'm currently implementing your work on text classification on 20news dataset. I'm using single Nvidia A6000 for this task with FedOPT algorithm, total client 50 and 2 clients per ro…
-
Hi, I am very interested in your work, is there no code with loss function L2 norm？
-
Hey, I am getting random aborts that I can't find the source of. I have a server and two clients.
I am getting them consistently at the 33 minute mark which makes it a bit hard to debug.
I have …
-
Hi, the aggregator config files generated for fedprox uses the iter average fusion handler. Is the Fedprox capability in the library incomplete or is it supposed to use the iter average fusion handler…
-
Hi, I am using Fedprox and testing model update at aggreator side.
I added 'model' property to 'examples/configs/fedprox/keras/config_agg.yml' as below.
In this case, 'start_global_training()' i…
-
FedProx of IBM FL requires to use TensorFlow2.1.0 ‘SavedModel’ Format.
I tried to test the following CNN model for FEMNIST dataset as the LEAF framework used.
But, it makes errors as below.
…
-
Hi, I read your paper and code, and this work has inspired me a lot in my work on Federated Learning Optimization. I am trying to reproduce FedProx using PyTorch and I am confused on a small detail. …
-
## Task scope
**We recommend you focus on the central claim of the paper.** For example, if a paper introduces a new RL learning algorithm that performs better in sparse-reward environments, verify t…