When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xia, Riting, Wang, Rucong, Liu, Yulin, Li, Anchen, Liu, Xueyan, Zhang, Yan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912500951285760
author Xia, Riting
Wang, Rucong
Liu, Yulin
Li, Anchen
Liu, Xueyan
Zhang, Yan
author_facet Xia, Riting
Wang, Rucong
Liu, Yulin
Li, Anchen
Liu, Xueyan
Zhang, Yan
contents Class-imbalanced graph node classification is a practical yet underexplored research problem. Although recent studies have attempted to address this issue, they typically assume clean and reliable labels when processing class-imbalanced graphs. This assumption often violates the nature of real-world graphs, where labels frequently contain noise. Given this gap, this paper systematically investigates robust node classification for class-imbalanced graphs with noisy labels. We propose GraphALP, a novel Graph Augmentation framework based on Large language models (LLMs) and Pseudo-labeling techniques. Specifically, we design an LLM-based oversampling method to generate synthetic minority nodes, producing label-accurate minority nodes to alleviate class imbalance. Based on the class-balanced graphs, we develop a dynamically weighted pseudo-labeling method to obtain high-confidence pseudo labels to reduce label noise ratio. Additionally, we implement a secondary LLM-guided oversampling mechanism to mitigate potential class distribution skew caused by pseudo labels. Experimental results show that GraphALP achieves superior performance over state-of-the-art methods on class-imbalanced graphs with noisy labels.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18153
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label
Xia, Riting
Wang, Rucong
Liu, Yulin
Li, Anchen
Liu, Xueyan
Zhang, Yan
Machine Learning
Artificial Intelligence
Class-imbalanced graph node classification is a practical yet underexplored research problem. Although recent studies have attempted to address this issue, they typically assume clean and reliable labels when processing class-imbalanced graphs. This assumption often violates the nature of real-world graphs, where labels frequently contain noise. Given this gap, this paper systematically investigates robust node classification for class-imbalanced graphs with noisy labels. We propose GraphALP, a novel Graph Augmentation framework based on Large language models (LLMs) and Pseudo-labeling techniques. Specifically, we design an LLM-based oversampling method to generate synthetic minority nodes, producing label-accurate minority nodes to alleviate class imbalance. Based on the class-balanced graphs, we develop a dynamically weighted pseudo-labeling method to obtain high-confidence pseudo labels to reduce label noise ratio. Additionally, we implement a secondary LLM-guided oversampling mechanism to mitigate potential class distribution skew caused by pseudo labels. Experimental results show that GraphALP achieves superior performance over state-of-the-art methods on class-imbalanced graphs with noisy labels.
title When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.18153