# Tackling the Imbalance for GNNs

arXiv: https://arxiv.org/abs/2110.08690 · HTML: https://mlsanity.com/paper/2110.08690/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 17 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [PairNorm: Tackling Oversmoothing in GNNs](https://mlsanity.com/paper/1909.12223/) (2019)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)
- [Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective](https://mlsanity.com/paper/2002.10826/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [The Devil is in the Tails: Fine-grained Classification in the Wild](https://mlsanity.com/paper/1709.01450/) (2017)
- [Imbalanced Deep Learning by Minority Class Incremental Rectification](https://mlsanity.com/paper/1804.10851/) (2018)
- [Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs](https://mlsanity.com/paper/2004.13465/) (2020)
- [GNN-XML: Graph Neural Networks for Extreme Multi-label Text Classification](https://mlsanity.com/paper/2012.05860/) (2020)

## Built on by (most cited first, 5 of 5)

- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Rethinking Class Imbalance in Machine Learning](https://mlsanity.com/paper/2305.03900/) (2023)
- [Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking](https://mlsanity.com/paper/2211.15538/) (2022)
- [Imbalanced Graph Classification with Multi-scale Oversampling Graph Neural Networks](https://mlsanity.com/paper/2405.04903/) (2024)
- [Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network](https://mlsanity.com/paper/2602.03808/) (2026)

## Abstract (arXiv)

Different from deep neural networks for non-graph data classification, graph neural networks (GNNs) leverage the information exchange between nodes (or samples) when representing nodes. The category distribution shows an imbalance or even a highly-skewed trend on nearly all existing benchmark GNN data sets. The imbalanced distribution will cause misclassification of nodes in the minority classes, and even cause the classification performance on the entire data set to decrease. This study explores the effects of the imbalance problem on the performances of GNNs and proposes new methodologies to solve it. First, a node-level index, namely, the label difference index (LDI), is defined to quantitatively analyze the relationship between imbalance and misclassification. The less samples in a class, the higher the value of its average LDI; the higher the LDI of a sample, the more likely the sample will be misclassified. We define a new loss and propose four new methods based on LDI. Experimental results indicate that the classification accuracies of the three among our proposed four new methods are better in both transductive and inductive settings. The LDI can be applied to other GNNs.