zhitao-wang / plnlp Goto Github PK

Thanks for your brilliant work about PLNLP. In the paper "Pairwise Learning for Neural Link Prediction", there exists the application of "Node-Pair Neighborhood Encoder" module, which is used to encode the subgraph corresponding to the target link. It seems that the project does not implement this module, is it because its effect is not obvious? Or is it too inefficient to run? Thank you.

Thanks for your excellent work on link prediction with GNNs. I have two questions about used tricks on ogbl-collab dataset.

For trick 'use_valedges_as_input':
I note that this trick in original OGB example script contains additional operations: During testing, to obtain scores on training and validation nodes, only raw training edges are used:

https://github.com/snap-stanford/ogb/blob/c8f0d2aca80a4f885bfd6ad5258ecf1c2d0ac2d9/examples/linkproppred/collab/gnn.py#L140

Then augmented training edges including validation edges are used to obtain test scores:

https://github.com/snap-stanford/ogb/blob/c8f0d2aca80a4f885bfd6ad5258ecf1c2d0ac2d9/examples/linkproppred/collab/gnn.py#L166

But in PLNLP implementation, the raw training edges have been replaced by augmented version including validation edges, which means that training, validation and test scores are all based on augmented training edges. The very 'high' reported validation scores (100%@50) seem over-fitted, which are supposed to be close to test scores (~70%@50).

For trick 'train_on_subgraph':
This trick limits the time range of training edges and validation edges to achieve better performance on test edges. However, it seems that test edges are also filtered (>=2010) in PLNLP. It is a bit confusing for me, since the test set is 'modified'.