无需训练，快速适应复杂图结构的标签传播方法。
F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel
- 基于局部聚类系数动态调整传播参数，实现自适应标签传播。
- 在多个数据集上精度媲美有监督GNN，速度提升数倍。
- 适合处理异质图且计算高效，适用于资源受限场景。
半监督节点分类是图机器学习的基础任务，但当前主流图神经网络（GNN）存在显著计算开销，并依赖强同质性假设。传统GNN需昂贵的迭代训练与多层消息传递，而现有无训练方法如标签传播难以适应异质图结构。本文提出F²LP-AP（Fast and Flexible Label Propagation with Adaptive Propagation Kernel），一种无需训练、计算高效的框架，可自适应局部图拓扑。该方法通过几何中位数构建稳健类别原型，并依据局部聚类系数（LCC）动态调整传播参数，有效建模同质与异质图结构，无需梯度训练。在多种基准数据集上的实验表明，F²LP-AP在精度上达到或超过有训练GNN水平，同时在计算效率上显著优于现有基线方法。
原文摘要 · Abstract (English)
Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by significant computational overhead and reliance on strong homophily assumptions. Traditional GNNs require expensive iterative training and multi-layer message passing, while existing training-free methods, such as Label Propagation, lack adaptability to heterophilo\-us graph structures. This paper presents \textbf{F$^2$LP-AP} (Fast and Flexible Label Propagation with Adaptive Propagation Kernel), a training-free, computationally efficient framework that adapts to local graph topology. Our method constructs robust class prototypes via the geometric median and dynamically adjusts propagation parameters based on the Local Clustering Coefficient (LCC), enabling effective modeling of both homophilous and heterophilous graphs without gradient-based training. Extensive experiments across diverse benchmark datasets demonstrate that \textbf{F$^2$LP-AP} achieves competitive or superior accuracy compared to trained GNNs, while significantly outperforming existing baselines in computational efficiency.
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。