kaft-neurips.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
14 hours	Rename method GRAFT → KAFT in user-facing README	YurenHao0426
	Internal code identifiers (GraphGrAPETrainer class, graft_* file prefixes, 'GRAFT' JSON dataset keys) are kept for backwards compatibility with results/ and earlier figure caches; a note at the top of the README points this out so reviewers don't get confused.
14 hours	Initial release: GRAFT (KAFT) — NeurIPS 2026 submission code	YurenHao0426
	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%.