facebookresearch / shaDow_GNN
NeurIPS 2021: Improve the GNN expressivity and scalability by decoupling the depth and receptive field of state-of-the-art GNN architectures
Summary
    |
|||
| Main Code: 7,535 LOC (93 files) = PY (64%) + YML (22%) + CPP (10%) + H (2%) + TOML (<1%) Secondary code: Test: 0 LOC (0); Generated: 0 LOC (0); Build & Deploy: 8 LOC (2); Other: 235 LOC (6); |
|||
| Duplication: 24% | |||
| File Size: 0% long (>1000 LOC), 42% short (<= 200 LOC) | |||
| Unit Size: 5% long (>100 LOC), 40% short (<= 10 LOC) | |||
| Conditional Complexity: 5% complex (McCabe index > 50), 48% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (12 components) | ||
|
|
10 months old
|
||
|
|
0% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits. |
||
| Goals: Keep the system simple and easy to change (4) | |||
|
Features of interest:
TODOs
11 files |
|||
Latest commit date: 2022-01-24
|
9
commits
(30 days)
1
contributors
(30 days) |
|