Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction

2026-01-24

AI Summary

This work proposes a graph structure-aware robust learning method to address the performance degradation of Graph Neural Networks (GNNs) under label noise in real-world scenarios. The approach introduces an influence inconsistency score as a novel noise metric, leveraging the graph diffusion matrix to capture inter-node dependencies. Building upon this, a Gaussian Mixture Model is employed to model the noise distribution, and a soft correction strategy is integrated with neighbor-based predictions to generate accurate pseudo-labels. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method significantly outperforms existing denoising techniques, effectively enhancing both the robustness and generalization capability of GNNs in noisy label settings.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Safety and Robustness
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data with various applications such as social analysis and bioinformatics. However, the presence of label noise in real scenarios poses a significant challenge in learning robust GNNs, and their effectiveness can be severely impacted when dealing with noisy labels on graphs, often stemming from annotation errors or inconsistencies. To address this, in this paper we propose a novel approach called ICGNN that harnesses the structure information of the graph to effectively alleviate the challenges posed by noisy labels. Specifically, we first design a novel noise indicator that measures the influence contradiction score (ICS) based on the graph diffusion matrix to quantify the credibility of nodes with clean labels, such that nodes with higher ICS values are more likely to be detected as having noisy labels. Then we leverage the Gaussian mixture model to precisely detect whether the label of a node is noisy or not. Additionally, we develop a soft strategy to combine the predictions from neighboring nodes on the graph to correct the detected noisy labels. At last, pseudo-labeling for abundant unlabeled nodes is incorporated to provide auxiliary supervision signals and guide the model optimization. Experiments on benchmark datasets show the superiority of our proposed approach.

Problem

• label noise
• Graph Neural Networks
• noisy labels
• robustness
• graph-structured data

Innovation

• Influence Contradiction Score
• Label Noise Correction
• Graph Neural Networks
• Gaussian Mixture Model
• Pseudo-labeling