# Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks

arXiv: https://arxiv.org/abs/2302.11479 · HTML: https://mlsanity.com/paper/2302.11479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 22 Feb 2023.

## Builds on (most cited first, 29 of 29)

- [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)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [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)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Understanding over-squashing and bottlenecks on graphs via curvature](https://mlsanity.com/paper/2111.14522/) (2021)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [A Gentle Introduction to Deep Learning for Graphs](https://mlsanity.com/paper/1912.12693/) (2019)
- [Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions](https://mlsanity.com/paper/2106.01798/) (2021)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Differentiable Graph Module (DGM) for Graph Convolutional Networks](https://mlsanity.com/paper/2002.04999/) (2020)
- [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)
- [DeBayes: a Bayesian Method for Debiasing Network Embeddings](https://mlsanity.com/paper/2002.11442/) (2020)
- [How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness](https://mlsanity.com/paper/1811.03654/) (2018)
- [Adaptive Propagation Graph Convolutional Network](https://mlsanity.com/paper/2002.10306/) (2020)
- [How Does Selective Mechanism Improve Self-Attention Networks?](https://mlsanity.com/paper/2005.00979/) (2020)
- [FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing](https://mlsanity.com/paper/2201.03681/) (2022)
- [Homophily and minority size explain perception biases in social networks](https://mlsanity.com/paper/1710.08601/) (2017)

## Built on by (most cited first, 2 of 2)

- [Migrate Demographic Group For Fair GNNs](https://mlsanity.com/paper/2306.04212/) (2023)
- [Estimating Fair Graphs from Graph-Stationary Data](https://mlsanity.com/paper/2510.07536/) (2025)

## Abstract (arXiv)

The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social impact. However, link prediction algorithms tend to increase the segregation in social networks by disfavoring the links between individuals in specific demographic groups. This paper proposes a novel way to enforce fairness on graph neural networks with a fine-tuning strategy. We Drop the unfair Edges and, simultaneously, we Adapt the model's parameters to those modifications, DEA in short. We introduce two covariance-based constraints designed explicitly for the link prediction task. We use these constraints to guide the optimization process responsible for learning the new "fair" adjacency matrix. One novelty of DEA is that we can use a discrete yet learnable adjacency matrix in our fine-tuning. We demonstrate the effectiveness of our approach on five real-world datasets and show that we can improve both the accuracy and the fairness of the link prediction tasks. In addition, we present an in-depth ablation study demonstrating that our training algorithm for the adjacency matrix can be used to improve link prediction performances during training. Finally, we compute the relevance of each component of our framework to show that the combination of both the constraints and the training of the adjacency matrix leads to optimal performances.