# Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation

arXiv: https://arxiv.org/abs/2512.06356 · HTML: https://mlsanity.com/paper/2512.06356/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications](https://mlsanity.com/paper/1709.07604/) (2017)
- [Deep Convolutional Networks on Graph-Structured Data](https://mlsanity.com/paper/1506.05163/) (2015)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning](https://mlsanity.com/paper/1908.02441/) (2019)
- [Inductive Matrix Completion Based on Graph Neural Networks](https://mlsanity.com/paper/1904.12058/) (2019)
- [On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features](https://mlsanity.com/paper/2111.12128/) (2021)
- [STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1905.13129/) (2019)
- [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)
- [Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank](https://mlsanity.com/paper/1906.06826/) (2019)
- [Incomplete Graph Representation and Learning via Partial Graph Neural Networks](https://mlsanity.com/paper/2003.10130/) (2020)
- [LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity](https://mlsanity.com/paper/2305.04225/) (2023)
- [Confidence-Based Feature Imputation for Graphs with Partially Known Features](https://mlsanity.com/paper/2305.16618/) (2023)
- [Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs](https://mlsanity.com/paper/2502.17912/) (2025)
- [Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification](https://mlsanity.com/paper/2410.16845/) (2024)

## Abstract (arXiv)

Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely on diffusion-based structural smoothing (e.g., feature propagation) to impute missing values. However, we find that these approaches suffer from structural overfitting, leading to three progressive challenges: 1) performance degradation on disjoint graphs, 2) loss of semantic diversity due to over-smoothing, and 3) feature distribution shift when generalizing to unseen graph structures (inductive tasks). To address these challenges, we introduce the DART framework. It begins by employing em Global Structural Augmentation (GSA), which establishes global correlations to bridge disjoint components and extend diffusion coverage. Building upon this, we design a semantic rectifier based on masked autoencoding. This module learns the latent feature manifold to recover natural semantic details. Crucially, we introduce a test-time distribution rectification mechanism that projects structurally biased features back onto the learned manifold during inference, effectively bridging the inductive distribution gap. Furthermore, considering that synthetic masking fails to reflect real-world sparsity, we present a new dataset Sailing collected from voyage records with naturally missing attributes. Extensive experiments on six public datasets and Sailing demonstrate that DART significantly outperforms state-of-the-art methods in both transductive and inductive settings. Our code and dataset are available at https://github.com/yfsong00/DART.