Robust OOD Graph Learning via Mean Constraints and Noise Reduction

TL;DR

This paper introduces two novel methods, CMO and NNR, to improve robustness and accuracy in graph out-of-distribution classification, especially under class imbalance and structural noise.

Contribution

The paper proposes Constrained Mean Optimization and Neighbor-Aware Noise Reweighting to enhance graph OOD classification robustness against imbalance and noise, with theoretical and empirical validation.

Findings

Significant accuracy improvements on synthetic and real datasets.

Enhanced robustness of minority classes in skewed distributions.

Effective noise mitigation through structural consistency weighting.

Abstract

Graph Out-of-Distribution (OOD) classification often suffers from sharp performance drops, particularly under category imbalance and structural noise. This work tackles two pressing challenges in this context: (1) the underperformance of minority classes due to skewed label distributions, and (2) their heightened sensitivity to structural noise in graph data. To address these problems, we propose two complementary solutions. First, Constrained Mean Optimization (CMO) improves minority class robustness by encouraging similarity-based instance aggregation under worst-case conditions. Second, the Neighbor-Aware Noise Reweighting (NNR) mechanism assigns dynamic weights to training samples based on local structural consistency, mitigating noise influence. We provide theoretical justification for our methods, and validate their effectiveness with extensive experiments on both synthetic and real-world datasets, showing significant improvements in Graph OOD generalization and classification accuracy. The code for our method is available at: https://anonymous.4open.science/r/CMO-NNR-2F30.