Yuwen Yang

Maybe you can refer to the config files for real-wolrd dataset.

For example, for task of "density" ``` { "data": { "task":"density" }, "tb": { "tb_logging":true, "dir":"tensorboard", "name": "S_density_optuna" }, "optuna":{ "opt_n_trials" : 50, "opt_n_cores" : 1, "monitor_metric" : "val_micro_f1", "opt_direction"...

> > > > When run `python prepare_dataset.py` ONCE **CONV =GIN and MINIBATCH =NeighborSampler** Regardless of the real-world dataset used, I got the following error message > > Using device:...

I agree with that. > > > The package ["python-graphviz"](https://github.com/mims-harvard/SubGNN/blob/eae0848b823cade135428b0ac264b7caa31862a1/SubGNN.yml#L174) does not exist in pip inventory. I assume the correct version is "[graphviz](https://pypi.org/project/graphviz/)" instead.

I find [**new solution**](https://github.com/rusty1s/pytorch_geometric/issues/1770) to this probleim https://github.com/rusty1s/pytorch_geometric/issues/1770#issuecomment-718461015 You should update your **torch-sparse >=0.6.4** just `pip install torch-sparse==0.6.4`

I'm honored that you enjoyed my work on summarizing information about FL open source frameworks. The table I put together leans more towards the basic information of each framework, and...

我注意到项目中说明“一年后会有重大版本更新”，可以询问进行到哪一步了吗？ （没错，我是来催更的 ^_^

> @youngfish42 Have you figured it out? Sorry, I have never successfully reproduced the experiment using the PPI_BP data set. For this reason, we removed the experiment on this data...

Thank you very much for your timely reply, and I look forward to your further compilation and analysis of the various federated learning frameworks. 😄

Very good proposal, looking forward to your contribution