IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors

TL;DR

IntraMix is a novel graph data augmentation technique that employs intra-class Mixup to generate high-quality labels and enrich node neighborhoods, improving GNN performance on limited and noisy data.

Contribution

It introduces IntraMix, a new method that combines intra-class Mixup with neighborhood enrichment, addressing label quality and neighborhood sparsity simultaneously in GNNs.

Findings

IntraMix improves accuracy across various GNN architectures.

The method effectively enhances neighborhood information and label quality.

Experimental results validate IntraMix's superiority over existing augmentation techniques.

Abstract

Graph Neural Networks (GNNs) have shown great performance in various tasks, with the core idea of learning from data labels and aggregating messages within the neighborhood of nodes. However, the common challenges in graphs are twofold: insufficient accurate (high-quality) labels and limited neighbors for nodes, resulting in weak GNNs. Existing graph augmentation methods typically address only one of these challenges, often adding training costs or relying on oversimplified or knowledge-intensive strategies, limiting their generalization. To simultaneously address both challenges faced by graphs in a generalized way, we propose an elegant method called IntraMix. Considering the incompatibility of vanilla Mixup with the complex topology of graphs, IntraMix innovatively employs Mixup among inaccurate labeled data of the same class, generating high-quality labeled data at minimal cost. Additionally, it finds data with high confidence of being clustered into the same group as the generated data to serve as their neighbors, thereby enriching the neighborhoods of graphs. IntraMix efficiently tackles both issues faced by graphs and challenges the prior notion of the limited effectiveness of Mixup in node classification. IntraMix is a theoretically grounded plug-in-play method that can be readily applied to all GNNs. Extensive experiments demonstrate the effectiveness of IntraMix across various GNNs and datasets. Our code is available at: https://github.com/Zhengsh123/IntraMix.