Showing cs.CEShow all
2 papers · 1 filter
cs.CE2026
GraphNetz: Statistical Benchmarking of Graph Neural Networks with Paired Tests and Rank Aggregation
Kleyton da Costa, Bernardo Modenesi
Graph Neural Networks (GNNs) benchmarks often report single point estimates, even when performance differences are small relative to variation across random seeds, train/test split…
cs.CE2026
Divergence-Guided Particle Swarm Optimization
Kleyton da Costa, Bernardo Modenesi, Ivan F. M. Menezes +1
Particle Swarm Optimization (PSO) is susceptible to premature convergence when the swarm collapses around the global best, particularly on multimodal landscapes in higher dimension…