Metraipolis › archive › dc_bd232d05535b

Propagate, Then Sharpen: Post-Hoc Refinement of Frozen Node Classifiers — arXiv:2609.35080

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35080
License (as archived)
CC0-1.0
Archived
2026-10-07T22:38:48.647Z
SHA-256 of the archived text
87be6b501e0afef79bd64c80529aa8b15c0691a66fdd3233bdd48382b1f659b3
Stable URL of this page
https://metraipolis.com/documento/dc_bd232d05535b

How to cite

Propagate, Then Sharpen: Post-Hoc Refinement of Frozen Node Classifiers — arXiv:2609.35080 — arXiv (en), https://arxiv.org/abs/2609.35080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd232d05535b (Metraipolis archive dc_bd232d05535b, sha256 87be6b501e0afef79bd64c80529aa8b15c0691a66fdd3233bdd48382b1f659b3)
BibTeX
@misc{dcbd232d05535b,
  title = {Propagate, Then Sharpen: Post-Hoc Refinement of Frozen Node Classifiers — arXiv:2609.35080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd232d05535b; sha256 87be6b501e0afef79bd64c80529aa8b15c0691a66fdd3233bdd48382b1f659b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study post-hoc refinement of frozen node classifiers: given only the graph $G$ and class distributions $Q$ predicted by a frozen model, can we improve accuracy without access to node features, model parameters, or gradients? APPNP answers this by propagating logits with a restart towards the initial predictions, minimizing the anchored Dirichlet energy. Instead, we consider the Potts energy, and decompose it into a Dirichlet term, which penalizes disagreement between neighbouring nodes, and a Gini term, which penalizes indecision within each node. This decomposition motivates Propagate, Then Sharpen (PtS), which alternates between propagation of class probabilities and node-wise, mass-preserving sharpening, with only one additional hyperparameter selected using labelled validation nodes. Across nine homophilic graphs, with a frozen MLP backbone, PtS improves mean test accuracy over independently tuned APPNP by $1.71$ percentage points on clean inputs and $3.90$ under severe Gaussian feature corruption. Gains over APPNP become smaller, but remain positive with frozen GCN and GraphSAGE backbones. Sharpening also removes most of the accuracy loss of deep propagation: on clean inputs without restart, accuracy falls by $2.2$ points between $2$ and $100$ propagation steps under PtS, compared with $33.8$ for APPNP.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.35080 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:28.347Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).