Graffin: Stand for Tails in Imbalanced Node Classification

TL;DR

Graffin is a plug-in module designed to enhance tail data representation in imbalanced graph neural network tasks, improving performance on underrepresented nodes without harming overall accuracy.

Contribution

Introduces Graffin, a novel tail data augmentation method inspired by RNNs, for better handling of imbalanced node classification in graphs.

Findings

Improves tail node classification accuracy.

Maintains overall model performance.

Effective across multiple real-world datasets.

Abstract

Graph representation learning (GRL) models have succeeded in many scenarios. Real-world graphs have imbalanced distribution, such as node labels and degrees, which leaves a critical challenge to GRL. Imbalanced inputs can lead to imbalanced outputs. However, most existing works ignore it and assume that the distribution of input graphs is balanced, which cannot align with real situations, resulting in worse model performance on tail data. The domination of head data makes tail data underrepresented when training graph neural networks (GNNs). Thus, we propose Graffin, a pluggable tail data augmentation module, to address the above issues. Inspired by recurrent neural networks (RNNs), Graffin flows head features into tail data through graph serialization techniques to alleviate the imbalance of tail representation. The local and global structures are fused to form the node representation under the combined effect of neighborhood and sequence information, which enriches the semantics of tail data. We validate the performance of Graffin on four real-world datasets in node classification tasks. Results show that Graffin can improve the adaptation to tail data without significantly degrading the overall model performance.