# NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration

arXiv: https://arxiv.org/abs/2505.15180 · HTML: https://mlsanity.com/paper/2505.15180/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 23 of 23)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks](https://mlsanity.com/paper/2106.02817/) (2021)
- [Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities](https://mlsanity.com/paper/1807.00123/) (2018)
- [TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2206.12917/) (2022)
- [LTE4G: Long-Tail Experts for Graph Neural Networks](https://mlsanity.com/paper/2208.10205/) (2022)
- [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)
- [Semi-supervised Domain Adaptation in Graph Transfer Learning](https://mlsanity.com/paper/2309.10773/) (2023)
- [Network Embedding with Completely-imbalanced Labels](https://mlsanity.com/paper/2007.03545/) (2020)
- [ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification](https://mlsanity.com/paper/2205.11332/) (2022)
- [GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification](https://mlsanity.com/paper/2302.12814/) (2023)
- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [Kernel-based Substructure Exploration for Next POI Recommendation](https://mlsanity.com/paper/2210.03969/) (2022)
- [Towards Continuous Reuse of Graph Models via Holistic Memory Diversification](https://mlsanity.com/paper/2406.07413/) (2024)
- [Cluster-guided Contrastive Class-imbalanced Graph Classification](https://mlsanity.com/paper/2412.12984/) (2024)
- [PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis](https://mlsanity.com/paper/2409.12728/) (2024)
- [Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learning](https://mlsanity.com/paper/2210.00162/) (2022)

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

- [UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning](https://mlsanity.com/paper/2605.09862/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have shown remarkable performance across various domains, yet they often struggle with model bias, particularly in the presence of class imbalance. This bias can lead to suboptimal performance and unfair predictions, especially for underrepresented classes. We introduce NeuBM (Neutral Bias Mitigation), a novel approach to mitigate model bias in GNNs through neutral input calibration. NeuBM leverages a dynamically updated neutral graph to estimate and correct the inherent biases of the model. By subtracting the logits obtained from the neutral graph from those of the input graph, NeuBM effectively recalibrates the model's predictions, reducing bias across different classes. Our method integrates seamlessly into existing GNN architectures and training procedures, requiring minimal computational overhead. Extensive experiments on multiple benchmark datasets demonstrate that NeuBM significantly improves the balanced accuracy and recall of minority classes, while maintaining strong overall performance. The effectiveness of NeuBM is particularly pronounced in scenarios with severe class imbalance and limited labeled data, where traditional methods often struggle. We provide theoretical insights into how NeuBM achieves bias mitigation, relating it to the concept of representation balancing. Our analysis reveals that NeuBM not only adjusts the final predictions but also influences the learning of balanced feature representations throughout the network.