Tag
The paper introduces CTQW-GNN, a graph neural network leveraging continuous-time quantum walks to address over-smoothing and improve performance on heterophilic graphs, demonstrating state-of-the-art results on benchmark datasets.
This paper proposes a K-Hop Gaussian (KHG) diffusion kernel as a preprocessing module for graph neural networks, balancing local and global information propagation to mitigate over-smoothing and information bottlenecks. Experiments show significant improvements over traditional message-passing GNNs and existing diffusion kernels, especially on noisy or structurally complex graphs.