FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation

ICLR 2026 Conference Submission12887 Authors

Keywords: incomplete graph learning, graph feature imputation, feature propagation

TL;DR: We propose a two-stage framework for graph feature imputation, comprising fractional subgraph diffusion and class-aware propagation steps, enabling robust representation learning, particularly in scenarios with high missing rates.

Abstract: 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. Code conducting all experiments can be found at https://anonymous.4open.science/r/FSD-CAP-50E8.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 12887