# Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks

arXiv: https://arxiv.org/abs/2408.12875 · HTML: https://mlsanity.com/paper/2408.12875/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 18 of 18)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Fairness in Deep Learning: A Computational Perspective](https://mlsanity.com/paper/1908.08843/) (2019)
- [Graph Neural Networks for Link Prediction with Subgraph Sketching](https://mlsanity.com/paper/2209.15486/) (2022)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Towards Fair Graph Neural Networks via Graph Counterfactual](https://mlsanity.com/paper/2307.04937/) (2023)
- [FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization](https://mlsanity.com/paper/2403.12474/) (2024)
- [Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification](https://mlsanity.com/paper/2312.04111/) (2023)
- [Chasing Fairness in Graphs: A GNN Architecture Perspective](https://mlsanity.com/paper/2312.12369/) (2023)
- [ChemicalX: A Deep Learning Library for Drug Pair Scoring](https://mlsanity.com/paper/2202.05240/) (2022)
- [Graph Fairness Learning under Distribution Shifts](https://mlsanity.com/paper/2401.16784/) (2024)
- [VITA: 'Carefully Chosen and Weighted Less' Is Better in Medication Recommendation](https://mlsanity.com/paper/2312.12100/) (2023)
- [Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation](https://mlsanity.com/paper/2402.15988/) (2024)
- [Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classification](https://mlsanity.com/paper/2308.09596/) (2023)

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

- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [Learning Fair Graph Representations with Multi-view Information Bottleneck](https://mlsanity.com/paper/2510.25096/) (2025)
- [Estimating Fair Graphs from Graph-Stationary Data](https://mlsanity.com/paper/2510.07536/) (2025)
- [Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information](https://mlsanity.com/paper/2512.03074/) (2025)
- [Fairness-Aware Network Embeddings: Methods, Applications, and Challenges](https://mlsanity.com/paper/2608.19381/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have become essential tools for graph representation learning in various domains, such as social media and healthcare. However, they often suffer from fairness issues due to inherent biases in node attributes and graph structure, leading to unfair predictions. To address these challenges, we propose a novel GNN framework, DAB-GNN, that Disentangles, Amplifies, and deBiases attribute, structure, and potential biases in the GNN mechanism. DAB-GNN employs a disentanglement and amplification module that isolates and amplifies each type of bias through specialized disentanglers, followed by a debiasing module that minimizes the distance between subgroup distributions. Extensive experiments on five datasets demonstrate that DAB-GNN significantly outperforms ten state-of-the-art competitors in terms of achieving an optimal balance between accuracy and fairness. The codebase of DAB-GNN is available at https://github.com/Bigdasgit/DAB-GNN