Add LPFormer model and example

[HarryShomer]

This pull request adds an implementation of the SOTA Link Prediction model LPFormer from the KDD'24 paper - LPFormer: An Adaptive Graph Transformer for Link Prediction.

Example

python examples/test_lpformer.py.

I am able to replicate the reported performance on ogbl-ppa.

The results are shown below. I use the same hyperparameters used in the paper. Results are over 5 seeds.

Reported	PyG
63.32 ± 0.6	63.15 ± 0.9

Testing

The tests for LPFormer can be found in test/nn/models/test_lpformer.py. They each pass.

Docs

I've also included the documentation for the code. It builds and renders correctly with Sphinx with no errors.

[codecov]

Codecov Report

Attention: Patch coverage is 89.27445% with 34 lines in your changes missing coverage. Please review.

Project coverage is 86.35%. Comparing base (50f5622) to head (0e059d2).
Report is 1 commits behind head on master.

Files with missing lines	Patch %	Lines
torch_geometric/nn/models/lpformer.py	89.24%	34 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #9956      +/-   ##
==========================================
- Coverage   87.03%   86.35%   -0.69%     
==========================================
  Files         490      491       +1     
  Lines       32432    32744     +312     
==========================================
+ Hits        28227    28275      +48     
- Misses       4205     4469     +264     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.