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

arXiv: https://arxiv.org/abs/2507.13741 · HTML: https://mlsanity.com/paper/2507.13741/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)
- [New Benchmarks for Learning on Non-Homophilous Graphs](https://mlsanity.com/paper/2104.01404/) (2021)
- [GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction](https://mlsanity.com/paper/2106.11133/) (2021)
- [GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions](https://mlsanity.com/paper/2005.05537/) (2020)
- [Class-Imbalanced Graph Learning without Class Rebalancing](https://mlsanity.com/paper/2308.14181/) (2023)
- [Imbalanced Graph Classification via Graph-of-Graph Neural Networks](https://mlsanity.com/paper/2112.00238/) (2021)
- [A simple yet effective baseline for non-attributed graph classification](https://mlsanity.com/paper/1811.03508/) (2018)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)
- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning](https://mlsanity.com/paper/2406.09870/) (2024)
- [Graph Size-imbalanced Learning with Energy-guided Structural Smoothing](https://mlsanity.com/paper/2412.17591/) (2024)

## Built on by (most cited first, 1 of 1)

- [Heterogeneous Graph Alignment for Joint Reasoning and Interpretability](https://mlsanity.com/paper/2601.22593/) (2026)

## Abstract (arXiv)

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× training acceleration.