-
I want to know how do you maintain the parameters of each large model (such as Bert) in the process of federated learning, such as the fedavg algorithm? Because before server aggregation, if you run f…
-
Hi,
I have a question on the experimental results in Table 1, about MNIST `pathological non-IID` setting w/ 100 clients.
It is very surprising that the accuracy of `FedAvg` on MNIST in this setting…
-
# SCAFFOLD
* **Title:** SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
* **Venue:** ICML 2020
* **Link to paper:** https://proceedings.mlr.press/v119/karimireddy20a.html
## Do you …
-
### What is your question?
Hello! I want to add data augmentation in clients' local datasets after spilt different clients. For example, add rotation or translation in clients' mnist datasets. Now …
-
Hi, your dataloader uses the default collate_fn in pytorch 0.4.1. This truncates every batch to the length of the shortest sentence in that batch. By extension your experiments are only operating on a…
-
Inspired from Flower's tutorial: https://colab.research.google.com/github/adap/flower/blob/main/tutorials/Flower-1-Intro-to-FL-PyTorch.ipynb#scrollTo=J4Em7BPNTXeX
Should run successfully in a Colab…
-
请问楼主的main.py文件跑出来提示 OSError: [Errno 22] Invalid argument 这个有人遇到吗
-
In [this](https://github.com/adap/flower/blob/main/examples/quickstart_huggingface/client.py) example for transformers, what loss function is used for training distilbert?
Is the loss function that…
-
Hello, I would like to ask when I run the code in /distributed/detection and find that the imported package in main_fedavg_yolo.py does not actually exist. For instance, the files in the model/detecti…
-
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