针对高缺失率图数据，提出分阶段特征补全方法，提升准确性与稳定性。
FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation
- 分两阶段：先局部子图扩散，再类别感知优化，抑制误差传播
- 99.5%特征缺失下，节点分类准确率达80.06%~81.01%，接近全量数据表现
- 适合处理极端稀疏、异质性强的复杂图数据，尤其适用于补全任务
在图结构中补全缺失节点特征极具挑战性，尤其在高缺失率情况下。现有基于隐表示或全局扩散的方法常因错误传播导致估计不可靠。本文提出FSD-CAP，一种两阶段框架，在五组基准数据集上，当99.5%特征缺失时，节点分类平均准确率为80.06%（结构型）和81.01%（均匀型），接近使用完整特征的标准GCN模型所达的81.31%；链接预测的AUC分别为91.65%（结构型）和92.41%（均匀型），接近完全观测下的95.06%。该方法通过图距离引导的子图扩展与分数扩散算子控制传播锐度，并引入伪标签与邻域熵实现类别感知精修，显著优于其他模型，尤其在大规模及异质图数据上表现突出。
原文摘要 · Abstract (English)
Imputing missing node features in graphs is challenging, particularly under high missing rates. Existing methods based on latent representations or global diffusion often fail to produce reliable estimates, and may propagate errors across the graph. We propose FSD-CAP, a two-stage framework designed to improve imputation quality under extreme sparsity. In the first stage, a graph-distance-guided subgraph expansion localizes the diffusion process. A fractional diffusion operator adjusts propagation sharpness based on local structure. In the second stage, imputed features are refined using class-aware propagation, which incorporates pseudo-labels and neighborhood entropy to promote consistency. We evaluated FSD-CAP on multiple datasets. With $99.5\%$ of features missing across five benchmark datasets, FSD-CAP achieves average accuracies of $80.06\%$ (structural) and $81.01\%$ (uniform) in node classification, close to the $81.31\%$ achieved by a standard GCN with full features. For link prediction under the same setting, it reaches AUC scores of $91.65\%$ (structural) and $92.41\%$ (uniform), compared to $95.06\%$ for the fully observed case. Furthermore, FSD-CAP demonstrates superior performance on both large-scale and heterophily datasets when compared to other models.
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。