Tutorial 7 (PyTorch) Graph Neural Networks: Non-linearity in the forward pass for the GCN Layer missing?

phlippe / uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

https://uvadlc-notebooks.readthedocs.io/en/latest/

MIT License

2.59k stars 590 forks source link

Tutorial 7 (PyTorch) Graph Neural Networks: Non-linearity in the forward pass for the GCN Layer missing? #147

Open choudharynishu opened 3 months ago

choudharynishu commented 3 months ago

According to the equation given before the implementation of the GCN Layer, the output after normalization should pass through a non-linearity but I don't see any non-linearity function used in the forward hook. Is this a mistake ?