Add node-wise normalization mode in LayerNorm

[lightaime]

This pull request adds the node-wise normalization mode in LayerNorm. If "graph" mode is used (by default), each graph will be considered as an element to be normalized. If "node" mode is used, each node will be considered as an element to be normalized.

[codecov]

Codecov Report

Merging #4944 (4af89d3) into master (db5e6d9) will decrease coverage by 1.94%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master    #4944      +/-   ##
==========================================
- Coverage   84.65%   82.71%   -1.95%     
==========================================
  Files         330      330              
  Lines       17885    17887       +2     
==========================================
- Hits        15141    14795     -346     
- Misses       2744     3092     +348     

Impacted Files	Coverage Δ
torch_geometric/nn/norm/layer_norm.py	100.00% <100.00%> (ø)
torch_geometric/nn/models/dimenet_utils.py	0.00% <0.00%> (-75.52%)	⬇️
torch_geometric/nn/models/dimenet.py	14.51% <0.00%> (-53.00%)	⬇️
torch_geometric/nn/conv/utils/typing.py	81.25% <0.00%> (-17.50%)	⬇️
torch_geometric/loader/neighbor_loader.py	85.62% <0.00%> (-9.38%)	⬇️
torch_geometric/nn/inits.py	67.85% <0.00%> (-7.15%)	⬇️
torch_geometric/nn/resolver.py	88.00% <0.00%> (-6.00%)	⬇️
torch_geometric/testing/decorators.py	96.66% <0.00%> (-3.34%)	⬇️
torch_geometric/testing/feature_store.py	97.22% <0.00%> (-2.78%)	⬇️
torch_geometric/io/tu.py	93.90% <0.00%> (-2.44%)	⬇️
... and 7 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update db5e6d9...4af89d3. Read the comment docs.

[rusty1s]

Super. Only left nitpicky comments :D

[lightaime]

Super. Only left nitpicky comments :D

Thanks! Looks cleaner.