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

TL;DR

This paper introduces the extbf{ extbackslash DART} framework to mitigate structural overfitting in missing feature imputation for graph learning, using global augmentation, semantic rectification, and distribution correction.

Contribution

It proposes a novel distribution-aware rectification framework with global augmentation and test-time distribution correction for improved missing feature imputation in graphs.

Findings

extbf{ extbackslash DART} outperforms state-of-the-art methods on six datasets.

The framework effectively bridges distribution gaps in inductive tasks.

Experiments on a new Sailing dataset demonstrate real-world applicability.

Abstract

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 \textbf{\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 \textbf{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.