diff options
| author | YurenHao0426 <blackhao0426@gmail.com> | 2026-05-04 23:05:16 -0500 |
|---|---|---|
| committer | YurenHao0426 <blackhao0426@gmail.com> | 2026-05-04 23:05:16 -0500 |
| commit | bd9333eda60a9029a198acaeacb1eca4312bd1e8 (patch) | |
| tree | 7544c347b7ac4e8629fa1cc0fcf341d48cb69e2e /experiments/run_bp_kaft_depth.py | |
Initial release: GRAFT (KAFT) — NeurIPS 2026 submission code
Topology-factorized Jacobian-aligned feedback for deep GNNs. Includes:
- src/: GraphGrAPETrainer (KAFT) + BP / DFA / DFA-GNN / VanillaGrAPE baselines
+ multi-probe alignment estimator + dataset / sparse-mm utilities.
- experiments/: 19 runners reproducing every figure / table in the paper.
- figures/: 4 generators + the 4 PDFs cited in the report.
- paper/: NeurIPS .tex and consolidated experiments_master notes.
Smoke test: 50-epoch Cora GCN L=4 gives BP 77.3% / KAFT 79.0%.
Diffstat (limited to 'experiments/run_bp_kaft_depth.py')
0 files changed, 0 insertions, 0 deletions