Added GKAN

[danielshin1]

Added GKAN: Graph Kolmogorov-Arnold Networks as introduced in paper by Mehrdad Kiamari, and Bhaskar Krishnamachari. and the Kolmogorov-Arnold Network comes from the work https://arxiv.org/pdf/2404.19756 and implementation of kan is here https://github.com/KindXiaoming/pykan.

[puririshi98]

this is good at a high level. however i want to see how it compares to existing work. Can you please update this example:
https://github.com/pyg-team/pytorch_geometric/blob/master/examples/ogbn_train.py#L31
to have a "--gnn-choice" arg parse option, with choices ["sage, gat, gatv3"]. and run all 3 in your environment to see how they compare. Please make the highest test acc the default. I can review a little closer once that initial test is done

[puririshi98]

also try to get the Ci to be all green (your unit test is failing)

[puririshi98]

@danielshin1, this is a great project, checking in if you still want to get it merged, see above for next steps

[puririshi98]

@danielshin1 circling back