GraphTorque: Torque-Driven Rewiring Graph Neural Network
This addresses graph learning inefficiencies for researchers and practitioners, though it appears incremental as it builds on existing rewiring methods.
The paper tackled the problem of inefficient message passing in graph neural networks due to native graph interactions by proposing a torque-driven hierarchical rewiring strategy, which outperformed state-of-the-art rewiring methods on benchmark datasets for both heterophilous and homophilous graphs.
Graph Neural Networks (GNNs) have emerged as powerful tools for learning from graph-structured data, leveraging message passing to diffuse information and update node representations. However, most efforts have suggested that native interactions encoded in the graph may not be friendly for this process, motivating the development of graph rewiring methods. In this work, we propose a torque-driven hierarchical rewiring strategy, inspired by the notion of torque in classical mechanics, dynamically modulating message passing to improve representation learning in heterophilous and homophilous graphs. Specifically, we define the torque by treating the feature distance as a lever arm vector and the neighbor feature as a force vector weighted by the homophily disparity between nodes. We use the metric to hierarchically reconfigure receptive field of each layer by judiciously pruning high-torque edges and adding low-torque links, suppressing the impact of irrelevant information and boosting pertinent signals during message passing. Extensive evaluations on benchmark datasets show that the proposed approach surpasses state-of-the-art rewiring methods on both heterophilous and homophilous graphs.