AI RESEARCH

On Efficient Scaling of GNNs via IO-Aware Layers Implementations

arXiv CS.AI

ArXi:2605.31500v1 Announce Type: cross Graph Neural Networks (GNNs) are bottlenecked by sparse, irregular memory access. Popular frameworks such as DGL and PyTorch Geometric general message passing, but complex layers often materialize edge-wise intermediates, increasing memory traffic and limiting scalability on large graphs. We take an I/O- and arithmetic-intensity--centric view and show that widely used layers fall into three kernel families: SpMM-based convolutions, reduction-based aggregations, and attention-based layers (GATv2/Graph Transformer.