Moritz Lampert

Sorry, maybe my minimal working example was a bit too minimal. I want to write a custom encoder with configurations that can then be configured using the `.yaml`-file. But if...

That works, thank you. But then what is a use case for [`config/example.py`](https://github.com/pyg-team/pytorch_geometric/blob/master/graphgym/custom_graphgym/config/example.py)? I tested it and it also works just by specifying it only where you suggested. By the...

I solved the issue by creating all my custom configs in the module's `__init__.py`. In your example, I would create it in `torch_geometric/graphgym/custom_graphgym/act/__init__.py`. Then it would exist when you try...

I already wrote a code snippet to efficently (in terms of runtime) index all edges in a specific time window (i.e. for `get_snapshot` in my understanding): ``` data_min_t = data.t.min().item()...

So there is a PyG method `TemporalData.snapshot(...)` which should work the same way as our intended `get_snapshot(...)`, but it was not working for me when I tried it. Now I...

I've been meaning to write a Jupyter notebook (see [here](https://github.com/pathpy/pathpyG/blob/main/docs/tutorial/multi_order_concepts.ipynb)) that explains the concepts that are now used for the order lifting and so on. Maybe we can combine both...

On that note, currently you get some kind of JSON error when you try to assign a `numpy.array` or a `torch.Tensor` to `node_label` because it is not hashable. It would...

BTW: This is related to #155

Could be closed due to #173, but best practice would be to merge it into #173 instead to have a clearer/cleaner merge history. @VinsRR can you either close it or...

The comments mark the tests that are still failing. Most of them are because the intended behaviour is unclear to me. @IngoScholtes maybe you can help clarify them.