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

arXiv: https://arxiv.org/abs/2601.18938 · HTML: https://mlsanity.com/paper/2601.18938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 30 of 33)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [GRAND: Graph Neural Diffusion](https://mlsanity.com/paper/2106.10934/) (2021)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks](https://mlsanity.com/paper/2001.06362/) (2020)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Dirichlet Energy Constrained Learning for Deep Graph Neural Networks](https://mlsanity.com/paper/2107.02392/) (2021)
- [Graph Representation Learning in Biomedicine](https://mlsanity.com/paper/2104.04883/) (2021)
- [On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features](https://mlsanity.com/paper/2111.12128/) (2021)
- [Graph Convolutional Networks for Graphs Containing Missing Features](https://mlsanity.com/paper/2007.04583/) (2020)
- [Learning on Attribute-Missing Graphs](https://mlsanity.com/paper/2011.01623/) (2020)
- [T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation](https://mlsanity.com/paper/2212.12738/) (2022)
- [Learnable Topological Features for Phylogenetic Inference via Graph Neural Networks](https://mlsanity.com/paper/2302.08840/) (2023)
- [Confidence-Based Feature Imputation for Graphs with Partially Known Features](https://mlsanity.com/paper/2305.16618/) (2023)
- [Accurate Node Feature Estimation with Structured Variational Graph Autoencoder](https://mlsanity.com/paper/2206.04516/) (2022)
- [Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks](https://mlsanity.com/paper/2305.00139/) (2023)
- [Robust transport over networks](https://mlsanity.com/paper/1603.08129/) (2016)
- [Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment](https://mlsanity.com/paper/2401.17859/) (2024)
- [GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets](https://mlsanity.com/paper/2306.03447/) (2023)
- [Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network](https://mlsanity.com/paper/2302.07524/) (2023)
- [Dealing with Missing Modalities in Multimodal Recommendation: a Feature Propagation-based Approach](https://mlsanity.com/paper/2403.19841/) (2024)
- [From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm](https://mlsanity.com/paper/2211.11761/) (2022)
- [AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning](https://mlsanity.com/paper/2305.03741/) (2023)

## Abstract (arXiv)

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.