# EqGNN: Equalized Node Opportunity in Graphs

arXiv: https://arxiv.org/abs/2108.08800 · HTML: https://mlsanity.com/paper/2108.08800/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 19 Aug 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting](https://mlsanity.com/paper/1802.07007/) (2018)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [DeBayes: a Bayesian Method for Debiasing Network Embeddings](https://mlsanity.com/paper/2002.11442/) (2020)
- [Node Embedding over Temporal Graphs](https://mlsanity.com/paper/1903.08889/) (2019)
- [Achieving Equalized Odds by Resampling Sensitive Attributes](https://mlsanity.com/paper/2006.04292/) (2020)
- [Conditional Network Embeddings](https://mlsanity.com/paper/1805.07544/) (2018)

## Built on by (most cited first, 7 of 7)

- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections](https://mlsanity.com/paper/2406.03052/) (2024)
- [Mitigating Degree Bias in Signed Graph Neural Networks](https://mlsanity.com/paper/2408.08508/) (2024)
- [tBDFS: Temporal Graph Neural Network Leveraging DFS](https://mlsanity.com/paper/2206.05692/) (2022)
- [Estimating Fair Graphs from Graph-Stationary Data](https://mlsanity.com/paper/2510.07536/) (2025)
- [A Boolean Function-Theoretic Framework for Expressivity in GNNs with Applications to Fair Graph Mining](https://mlsanity.com/paper/2601.12751/) (2026)
- [Geometrical fairness in graph neural networks](https://mlsanity.com/paper/2606.17684/) (2026)

## Abstract (arXiv)

Graph neural networks (GNNs), has been widely used for supervised learning tasks in graphs reaching state-of-the-art results. However, little work was dedicated to creating unbiased GNNs, i.e., where the classification is uncorrelated with sensitive attributes, such as race or gender. Some ignore the sensitive attributes or optimize for the criteria of statistical parity for fairness. However, it has been shown that neither approaches ensure fairness, but rather cripple the utility of the prediction task. In this work, we present a GNN framework that allows optimizing representations for the notion of Equalized Odds fairness criteria. The architecture is composed of three components: (1) a GNN classifier predicting the utility class, (2) a sampler learning the distribution of the sensitive attributes of the nodes given their labels. It generates samples fed into a (3) discriminator that discriminates between true and sampled sensitive attributes using a novel "permutation loss" function. Using these components, we train a model to neglect information regarding the sensitive attribute only with respect to its label. To the best of our knowledge, we are the first to optimize GNNs for the equalized odds criteria. We evaluate our classifier over several graph datasets and sensitive attributes and show our algorithm reaches state-of-the-art results.