Zhenheng TANG

Hi, questions about the BROADCAST time and REDUCE time.

1

Hi, I'm curious about why the REDUCE time is different with BROADCAST time.  And, the BROADCAST time of each partition is different with others.  Could the reason be...

Hi, thanks for your awesome work! I noticed that the results in the paper: PYHESSIAN: Neural Networks Through the Lens of the Hessian, the tr(H) keeps increasing during training. ...

Could you add more servers in FedAvg for faster training speed?

10

Could you add more servers in FedAvg for faster training speed? As the BytePS does.

Questions about the test_metrics() functions and the partition between train and test.

1

Thanks for your awesome libs, including so many algorithms. I have a question about the evaluate function in the serverbase.py: https://github.com/TsingZ0/PFL-Non-IID/blob/fd23a2124265fac69c137b313e66e45863487bd5/system/flcore/servers/serverbase.py#L165 It seems that in each round, the test will...

### What is your question? Hi, thanks for your awesome framework. Could you provide the code of FEMNIST baseline used in the paper? I'm trying to benchmark the running time...

### What is your question? Thanks for your awesome frameworks! I hope to conduct experiments of FEMNSIT and Amazon’s Book Reviews. Could you please indicate where can I get these...

Draft of New Trainer and Aggregator

Dev/v0.7.0

3

Complete Sequentral Training

Hi, could you give me the specific 100 classes of ImageNet-100 that you use?

1

Thank you for your awesome works! I also want to use ImageNet-100 for experiments. Could you give me the specific 100 classes of ImageNet-100 that you use?

Could you please provide your codes of conducting other baseline methods? That would be very helpful for others to follow this interesting work. And it seems that current codes have...