RAwR: Role-Aware Rewiring via Approximate Equitable Partition

ArXi:2605.09457v1 Announce Type: cross While Graph Neural Networks (GNNs) have nstrated significant efficacy in node classification tasks, where predictions rely on local neighborhood information, the performance of GNNs often drops when prediction tasks depend on long-range interactions. These limitations are attributed to phenomena such as oversquashing, where structural bottlenecks restrict signal propagation across the network topology. To address this challenge, we