Fix bugs in PNAConv and DegreeScalerAggregation

[zechengz]

Some fixes, including bugs fixes and minor documentation fixes

torch_geometric/nn/aggr/scaler.py

The deg tensor should be clamped during the inverse_linear computation and thus avoid division by zero (in case the deg tensor contains a zero degree value). Previous implementation will make the zero degree value equal to two in the amplification and attenuation cases where we also add one directly. Though I am not sure whether this way is correct and whether we also need to clamp(1) in the linear scaler.

torch_geometric/nn/conv/pna_conv.py

The previous implementation utilized two for loops to compute the deg_histogram tensor. The first loop calculates the max_degree, while the second loop updates the deg_histogram by adding each bincount, with a minlength of max_degree + 1. However, for certain loaders (e.g. the NeighborLoader), the degree in the second loop may exceed the max_degree computed in the first loop and thus raise following error. Also, current implementation that replaces the two loops with one loop may potentially improve computation speed, although I don't verify this...

    deg_histogram += torch.bincount(d, minlength=deg_histogram.numel())
RuntimeError: The size of tensor a (17) must match the size of tensor b (19) at non-singleton dimension 0

[codecov]

Codecov Report

Merging #6609 (a930b6d) into master (a930b6d) will not change coverage.
The diff coverage is n/a.

❗ Current head a930b6d differs from pull request most recent head 90f3da5. Consider uploading reports for the commit 90f3da5 to get more accurate results

@@           Coverage Diff           @@
##           master    #6609   +/-   ##
=======================================
  Coverage   87.40%   87.40%           
=======================================
  Files         421      421           
  Lines       22903    22903           
=======================================
  Hits        20018    20018           
  Misses       2885     2885           

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[rusty1s]

Thanks!