Viet Trong Nguyen

Valid for Free: Homophily-Gated Conformal Prediction for Training-Free Node Classification with Tabular Foundation Models

This work gives the first reliability study of the TabICL setting, with TabICL as the TFM and half of each graph as labeled context, and introduces HG-DAPS, a training-free diffusion score whose homophily gate reads only the in-context labels, so the guarantee still holds.