Devansh Amin

Thank you @AzureLeon1 for taking the time to review the PR. Regarding the `BatchGRU`, I have few thoughts - 1. If you look at the forward method of the [AttentiveFP](https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/models/attentive_fp.py#L162-L166),...

@mayabechlerspeicher You can utilize the `exclude_keys` in the `CustomBatch.from_data_list(...)` and add it to the `batch` however you want. ```python from typing import List, Optional, Union, Sequence import random import torch...

> Hey @devanshamin Thank you so much for flagging and suggesting improvements! We agree with everything you mentioned. If it helps, one design decision we have adopted is that when...

Here is an article outlining steps on merging this PR - https://github.com/ShishirPatil/gorilla/discussions/521

## Potential cause I suspect the issue is due to the loading of wrong `Sequential` module likely due to the random `uid` being used to generate the [/tmp/torch_geometric.nn.sequential_{uid}.py](https://github.com/pyg-team/pytorch_geometric/blob/2.5.2/torch_geometric/nn/sequential.py#L126-L136) file. ##...

Your original code should work fine if you install PyG from source (`pip install git+https://github.com/pyg-team/pytorch_geometric.git`). Recent version of PyG 2.6.0 contains `Sequential` module that has been refactored, - Logic of...

Hi @rusty1s , I can work on creating an example implementation of this feature in PyG.

PR should be up by end of this week.