SyncAI.news, a Varaisys broadcasting
Propagate, Then Sharpen: Post-Hoc Refinement of Frozen Node Classifiers
PJ

Preben Johnsen Bentdal, Nello Blaser, Xue-Cheng Tai

· 1 min read

ResearcharXiv cs.LG

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

arXiv:2609.35080v1 Announce Type: new Abstract: 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.

Original source

This story was published by arXiv cs.LG and written by Preben Johnsen Bentdal, Nello Blaser, Xue-Cheng Tai. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News