Matthias Fey

This is clever. Do you want to contribute this feature? :)

Thanks!

I think this would be way easier if we would just return the edge indices in `random_walk` :( I guess your approach works, but will be indeed inefficient.

If you are interested, we can add support for this in [`pyg-lib`](https://pyg-lib.readthedocs.io/en/latest/modules/sampler.html#pyg_lib.sampler.random_walk), which should be straightforward to add. It also supports nightly builds so it should be ready to use...

Reference: #139 Thanks @pbielak!

There is a typo in the URL (should be https://data.pyg.org/whl/torch-1.12.0+cu113.html) - might this explain your issues? If you download one of the wheels, you can see that the `_cuda.so` files...

Yes, that is correct. Importantly, `batches` denotes a list of contiguous node indices grouped that we want to group into one single mini-batch/subgraph, for example: `[[0, 1, 2], [5, 6,...

Did you run `python setup.py install` before executing the scripts?

Can you try to run the script not within the root folder, but within `small_benchmark`? ``` cd small_benchmark python main.py ```

This is weird. What's the installation log of ``` python setup.py clean && python setup.py develop ```