SamGoG: A Sampling-Based Graph-of-Graphs Framework for Imbalanced Graph Classification

TL;DR

SamGoG introduces a sampling-based framework that constructs multiple graph-of-graphs to effectively address class and size imbalances in graph classification, improving accuracy and efficiency.

Contribution

It proposes a novel importance-based sampling method for constructing multiple GoGs, enhancing GNN performance on imbalanced graph classification tasks.

Findings

Achieves up to 15.66% accuracy improvement

Provides 6.7× faster training

Demonstrates state-of-the-art results on benchmarks

Abstract

Graph Neural Networks (GNNs) have shown remarkable success in graph classification tasks by capturing both structural and feature-based representations. However, real-world graphs often exhibit two critical forms of imbalance: class imbalance and graph size imbalance. These imbalances can bias the learning process and degrade model performance. Existing methods typically address only one type of imbalance or incur high computational costs. In this work, we propose SamGoG, a sampling-based Graph-of-Graphs (GoG) learning framework that effectively mitigates both class and graph size imbalance. SamGoG constructs multiple GoGs through an efficient importance-based sampling mechanism and trains on them sequentially. This sampling mechanism incorporates the learnable pairwise similarity and adaptive GoG node degree to enhance edge homophily, thus improving downstream model quality. SamGoG can seamlessly integrate with various downstream GNNs, enabling their efficient adaptation for graph classification tasks. Extensive experiments on benchmark datasets demonstrate that SamGoG achieves state-of-the-art performance with up to a 15.66% accuracy improvement with 6.7$\times$ training acceleration.