# Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics

arXiv: https://arxiv.org/abs/2607.14705 · HTML: https://mlsanity.com/paper/2607.14705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [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)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Learning from Failure: Training Debiased Classifier from Biased Classifier](https://mlsanity.com/paper/2007.02561/) (2020)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders](https://mlsanity.com/paper/2205.10053/) (2022)
- [FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning](https://mlsanity.com/paper/2104.14210/) (2021)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [Fundamental Limits and Tradeoffs in Invariant Representation Learning](https://mlsanity.com/paper/2012.10713/) (2020)
- [FairGT: A Fairness-aware Graph Transformer](https://mlsanity.com/paper/2404.17169/) (2024)
- [FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization](https://mlsanity.com/paper/2403.12474/) (2024)
- [The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation](https://mlsanity.com/paper/2311.17373/) (2023)
- [ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting](https://mlsanity.com/paper/2205.13700/) (2022)
- [Fair Graph Representation Learning via Sensitive Attribute Disentanglement](https://mlsanity.com/paper/2405.07011/) (2024)
- [FUGNN: Harmonizing Fairness and Utility in Graph Neural Networks](https://mlsanity.com/paper/2405.17034/) (2024)
- [Rethinking Fair Graph Neural Networks from Re-balancing](https://mlsanity.com/paper/2407.11624/) (2024)
- [FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning](https://mlsanity.com/paper/2412.10669/) (2024)
- [Graph Fairness Learning under Distribution Shifts](https://mlsanity.com/paper/2401.16784/) (2024)
- [One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes](https://mlsanity.com/paper/2406.13544/) (2024)
- [Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmark](https://mlsanity.com/paper/2403.06017/) (2024)
- [Fairness without Demographics through Learning Graph of Gradients](https://mlsanity.com/paper/2412.03706/) (2024)
- [Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributes](https://mlsanity.com/paper/2412.09947/) (2024)
- [FairGSE: Fairness-Aware Graph Neural Network without High False Positive Rates](https://mlsanity.com/paper/2511.12132/) (2025)

## Abstract (arXiv)

Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted demographics as proxies to enforce fairness constraints. However, predicted demographics may be inaccurate, resulting in the failure to improve fairness. In this work, we investigate the problem of graph fairness without demographic information and avoid the utilization of predicted demographics. Motivated by our observation that the gradient distributions of misclassified nodes implicitly encode demographic information, we first propose GradDist, a gradient-based metric that quantifies bias by measuring the distance between local modes within these distributions. To mitigate this bias, we propose Gradient-to-Fairness (Grad2Fair), a gradient-guided approach for group fairness without demographics. Due to the potential demographics in gradients, Grad2Fair directly leverages gradients to debias and eliminates demographic prediction, thereby enabling stable fairness performance. Experiments on several real-world datasets demonstrate the effectiveness of Grad2Fair, as evidenced by superior performance over baselines in most cases. Our code is available at https://github.com/ZzoomD/Grad2Fair.