← Search

Peng Huo

2 accepted papers

2026

Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space

ICLR 2026poster

Post-hoc instance-level graph neural network (GNN) explainers are developed to identify a compact subgraph (i.e., explanation) that encompasses the most influential components for each input graph. A fundamental limitation of existing methods lies in the insufficient utilization of structural inform…

Cited by 0SourcecodeScholar
2026

Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases

ICML 2026poster

In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect t…

Cited by 0SourceScholar