# Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Study

arXiv: https://arxiv.org/abs/2608.09899 · HTML: https://mlsanity.com/paper/2608.09899/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [A critical look at the evaluation of GNNs under heterophily: Are we really making progress?](https://mlsanity.com/paper/2302.11640/) (2023)
- [Fairness of Exposure in Rankings](https://mlsanity.com/paper/1802.07281/) (2018)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification](https://mlsanity.com/paper/2406.08993/) (2024)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [On Formalizing Fairness in Prediction with Machine Learning](https://mlsanity.com/paper/1710.03184/) (2017)
- [Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond](https://mlsanity.com/paper/2209.06177/) (2022)
- [Quantifying the Impact of User Attention on Fair Group Representation in Ranked Lists](https://mlsanity.com/paper/1901.10437/) (2019)
- [When Fair Ranking Meets Uncertain Inference](https://mlsanity.com/paper/2105.02091/) (2021)
- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [Correcting Exposure Bias for Link Recommendation](https://mlsanity.com/paper/2106.07041/) (2021)
- [FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification](https://mlsanity.com/paper/2201.11596/) (2022)
- [Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction](https://mlsanity.com/paper/2309.17417/) (2023)
- [A Clarified Typology of Core-Periphery Structure in Networks](https://mlsanity.com/paper/2005.10191/) (2020)
- [Inequality and Inequity in Network-based Ranking and Recommendation Algorithms](https://mlsanity.com/paper/2110.00072/) (2021)
- [Link recommendations: Their impact on network structure and minorities](https://mlsanity.com/paper/2205.06048/) (2022)
- [The Datafication of Care in Public Homelessness Services](https://mlsanity.com/paper/2502.09043/) (2025)
- [A Recommendation and Risk Classification System for Connecting Rough Sleepers to Essential Outreach Services](https://mlsanity.com/paper/2007.15326/) (2020)
- [Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity](https://mlsanity.com/paper/2511.06568/) (2025)

## Abstract (arXiv)

In fair ranked link prediction, demographic parity (DeltaDP) is a common fairness metric. Yet, Mattos et al. (2025) argue that it fails to detect exposure bias because it ignores where links appear in the ranking. In this study, we reproduce this claim by showing that DeltaDP can indicate aggregate parity even when some subgroup-pair links are systematically ranked lower than others. The proposed rank-aware Normalized Discounted KL-divergence (NDKL), however, does detect such disparities. We also reproduce the effectiveness of MORAL, a post-processing method that improves exposure-based fairness while maintaining competitive utility. Beyond reproduction, we assess robustness using synthetic homophily settings, categorical sensitive attributes, and additional fairness and utility metrics, including subgroup-pair-adapted Attention-Weighted Rank Fairness (AWRF). Overall, our results show that exposure-based metrics uncover biases hidden by DeltaDP and that MORAL reduces these biases with minimal utility loss across diverse settings and datasets. We release a corrected, reproducible implementation at https://github.com/Floris93100/reproducing-MORAL.