Add temporal sampling support to NeighborLoader

[RexYing]

not sure how to use the parameterize thing yet.

I was trying
@pytest.mark.parametrize('directed', [True, False])
@pytest.mark.parametrize('temporal', [True, False])
but didn't work. Will look into it further.

[rusty1s]

I was trying
@pytest.mark.parametrize('directed', [True, False])
@pytest.mark.parametrize('temporal', [True, False])
but didn't work. Will look into it further.

This should work, but keep in mind to add both directed and temporal to the function signature.

[rusty1s]

This looks pretty good! Left some last comments.

[codecov]

Codecov Report

Merging #4025 (fb680be) into master (c3d1ac5) will decrease coverage by 0.12%.
The diff coverage is 83.33%.

@@            Coverage Diff             @@
##           master    #4025      +/-   ##
==========================================
- Coverage   82.83%   82.71%   -0.13%     
==========================================
  Files         313      313              
  Lines       16343    16361      +18     
==========================================
- Hits        13538    13533       -5     
- Misses       2805     2828      +23     

Impacted Files	Coverage Δ
torch_geometric/data/lightning_datamodule.py	26.08% <ø> (ø)
torch_geometric/loader/neighbor_loader.py	91.83% <75.00%> (-2.61%)	⬇️
torch_geometric/testing.py	96.66% <91.66%> (-3.34%)	⬇️
torch_geometric/nn/conv/utils/typing.py	81.25% <0.00%> (-17.50%)	⬇️
torch_geometric/io/tu.py	93.58% <0.00%> (-2.57%)	⬇️
torch_geometric/nn/models/mlp.py	98.41% <0.00%> (-1.59%)	⬇️
torch_geometric/transforms/gdc.py	78.17% <0.00%> (-1.02%)	⬇️
torch_geometric/data/dataset.py	96.80% <0.00%> (-0.80%)	⬇️
torch_geometric/nn/conv/rgat_conv.py	83.76% <0.00%> (-0.53%)	⬇️
torch_geometric/graphgym/utils/comp_budget.py	15.51% <0.00%> (+0.51%)	⬆️

---

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 c3d1ac5...fb680be. Read the comment docs.