# Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks

arXiv: https://arxiv.org/abs/2406.17073 · HTML: https://mlsanity.com/paper/2406.17073/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction](https://mlsanity.com/paper/1903.04233/) (2019)
- [Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks](https://mlsanity.com/paper/1812.09464/) (2018)
- [Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty](https://mlsanity.com/paper/1901.11213/) (2019)
- [StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks](https://mlsanity.com/paper/2009.14337/) (2020)

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

- [GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance](https://mlsanity.com/paper/2510.20671/) (2025)

## Abstract (arXiv)

Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be biased towards the majority class(es). Conventional methods typically tackle this problem through the assignment of weights to each one of the class samples based on a function of their loss, which can lead to over-fitting on outliers. In this paper, we propose a meta-learning algorithm, named Meta-GCN, for adaptively learning the example weights by simultaneously minimizing the unbiased meta-data set loss and optimizing the model weights through the use of a small unbiased meta-data set. Through experiments, we have shown that Meta-GCN outperforms state-of-the-art frameworks and other baselines in terms of accuracy, the area under the receiver operating characteristic (AUC-ROC) curve, and macro F1-Score for classification tasks on two different datasets.