用高斯加权多跳扩散增强GNN，提升噪声图上的表现
Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion
- 引入多跳高斯扩散，平衡局部与全局信息传播
- 在多个基准数据集上超越传统GNN及PPR、热核方法
- 适合处理噪声大或结构复杂的图数据
现有图神经网络核心依赖于邻接节点间的消息传递，但在真实图中边常含噪声或定义不清，限制了信息传播范围。尽管个人化页面排名（PPR）和热核等扩散核能实现全局传播，仍难以应对复杂局部结构和远距离噪声。为此，我们提出一种用于图数据预处理的K-Hop高斯（KHG）扩散核，通过高斯加权的多跳扩散，融合远程节点信息，在标准GNN前实现更优的信息传播。在多个基准数据集上的实验表明，该方法显著优于传统消息传递GNN以及PPR、热核扩散，尤其在噪声较大或结构复杂的图中表现更佳。
原文摘要 · Abstract (English)
Most graph neural network (GNN) cores rely on graph convolutions, typically implemented as message passing between direct (single-hop) neighbors. In many real-world graphs, edges can be noisy or poorly defined, limiting information propagation to local neighborhoods. Existing diffusion kernels, such as Personalized PageRank (PPR) and Heat Kernel, alleviate this issue through global propagation, but still struggle with complex local structures and distant node noise. To address these limitations, we propose a K-Hop Gaussian (KHG) diffusion kernel as a preprocessing module for graph data. KHG introduces multi-hop diffusion with Gaussian weighting for remote nodes, balancing local and global information propagation before applying standard GNNs. Experiments on multiple benchmark datasets demonstrate that KHG significantly outperforms traditional message-passing GNNs, as well as PPR and Heat Kernel diffusion, particularly in noisy or structurally complex graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。