When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice
TL;DR
The results suggest that benchmark composition, rather than numerical insufficiency, determines whether design rules appear to generalize, and that the Facebook-100 regime provides a concrete target for future adaptive aggregation methods.
Abstract
We examine whether graph neural network (GNN) design rules generalize across benchmark families by studying aggregator selection (sum, mean, max) on 24 node-classification datasets spanning citation, heterophilic, LINKX Facebook-100, co-purchase, and co-authorship graphs. Edge homophily is only weakly predictive of the GIN-Sum versus GIN-Mean performance gap. Label informativeness predicts this gap well on legacy benchmarks but degrades substantially when Facebook-100 graphs are included. In these dense friendship networks, near-zero label informativeness coexists with a strong preference for sum aggregation, producing gains of 7-10% and up to 13% under extended training. Stochastic block model ablations, including degree-corrected variants matching Facebook-100 degree scales, fail to reproduce this behavior, indicating that mean degree alone does not explain the effect. Among several label-independent graph statistics, the spectral gap uniquely distinguishes these graphs from other low-informativeness datasets, with the effect localized to one-hop neighborhoods and replicated across architectures. We further identify training regimes that interact with aggregator choice and show that PNA can underperform the best single-aggregator GIN on standard citation benchmarks. Our results suggest that benchmark composition, rather than numerical insufficiency, determines whether design rules appear to generalize, and that the Facebook-100 regime provides a concrete target for future adaptive aggregation methods.