When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label
By: Riting Xia , Rucong Wang , Yulin Liu and more
Potential Business Impact:
Fixes computer problems with messy, incomplete data.
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.
Similar Papers
Large Language Models for Imbalanced Classification: Diversity makes the difference
Machine Learning (CS)
Makes computer learning better with more varied examples.
Optimal Labeler Assignment and Sampling for Active Learning in the Presence of Imperfect Labels
Machine Learning (CS)
Finds the best data to teach computers, ignoring bad answers.
GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance
Machine Learning (CS)
Makes computer learning better for rare things.