← Search

Yuneil Yeo

2 accepted papers

2025

Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features

ICLR 2025poster

Diffusion-based imputation methods, which impute missing features through the iterative propagation of observed features, have shown impressive performance in homogeneous graphs. However, these methods are not directly applicable to heterogeneous graphs, which have multiple types of nodes and edges,…

2025

Spreading Out-of-Distribution Detection on Graphs

ICLR 2025poster

Node-level out-of-distribution (OOD) detection on graphs has received significant attention from the machine learning community. However, previous approaches are evaluated using unrealistic benchmarks that consider only randomly selected OOD nodes, failing to reflect the interactions among nodes. In…