-
I would like to ask if Fedopt is only available in the simulation mode? Is there any way to use it in the cross-silo mode with MQTT as FedAvg.
Thanks
-
in fedml_api folder, fedopt's FedOptClientManager and FedOptTrainer are almost same to those of fedavg. But, in fedopt paper, clients should return the delta weights to server. Btw, server optimizer i…
-
### Describe the bug
When I use any of the FedOpt strategies (FedAdam, FedYogi, FedAdagrad) it seems very unstable, the model outputs NaNs after second/third aggregation.
### Steps/Code to Repr…
-
Hello, I have a question.Do you implement the Fedadagrad, FedYogi, FedAdam algorithm of the paper "Adaptive Federated Optimization" in the code fedopt?
-
Hi
I tried to use other strategy rather than fedavg.
I simply change fl.server.strategy.FedAvg to fl.server.strategy.FedAdagrad in the sample code (advanced_tensorflow/server.py).
And also change o…
-
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…
-
Hi Chaoyang! @chaoyanghe @yuchenlin
I try to reproduce some results in [FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks](https://arxiv.org/abs/2104.08815).
I f…
-
Hi,
Thanks for starting the refactoring. Here are a few comments to go even further. I will not mark anything as compulsory given the time constraints, but it would be great to save what will not b…
-
I am trying to reproduce the FedAvg results on 20news data. However, the FedAvg algorithm on 20news task seems not working. Comparing with the centralized run, the eval accuracy and loss of FedAvg did…