FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening

ArXi:2410.15001v5 Announce Type: replace Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation trees are used to train on a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during the inference phase using graph coarsening. We nstrate two different methods -- Extra Nodes and Cluster Nodes.