Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants

Understand

Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs).

• Increasing the GNN depth can expand the scope (i.e., receptive field), potentially finding homophily from the higher-order neighborhoods.
• However, GNNs suffer from performance degradation as depth increases.
• Despite having better expressivity, state-of-the-art deeper GNNs achieve only marginal improvements compared to their shallow variants.