SOURCE-LINKED INTELLIGENCE

HOPE: Heterophily-Aware Open-Set Node Classification with Pseudo-Extrapolation

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Standard open-set node classification methods rely on the homophily assumption, where connected nodes share labels. However, real-world graphs are often heterophilic, exposing the limitations of current methods and posing new challenges to open-set node classification. On the one hand, cross-class connectivity causes representations from different known or unknown classes to become intertwined after aggregation, undermining their discriminative capacity. On the other hand, structural mixture invalidates threshold-based open-set methods and cross-class feature interpolation, leading to unreliab

Read original source ↗ Open in workspace

recordType

paper

region

Global