# Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity

arXiv: https://arxiv.org/abs/2511.06568 · HTML: https://mlsanity.com/paper/2511.06568/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 57 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Builds on (most cited first, 30 of 33)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Fairness of Exposure in Rankings](https://mlsanity.com/paper/1802.07281/) (2018)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [FA*IR: A Fair Top-k Ranking Algorithm](https://mlsanity.com/paper/1706.06368/) (2017)
- [Graph Neural Networks for Link Prediction with Subgraph Sketching](https://mlsanity.com/paper/2209.15486/) (2022)
- [Ranking with Fairness Constraints](https://mlsanity.com/paper/1704.06840/) (2017)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Policy Learning for Fairness in Ranking](https://mlsanity.com/paper/1902.04056/) (2019)
- [Neural Common Neighbor with Completion for Link Prediction](https://mlsanity.com/paper/2302.00890/) (2023)
- [Fair and Optimal Classification via Post-Processing](https://mlsanity.com/paper/2211.01528/) (2022)
- [Neural Link Prediction with Walk Pooling](https://mlsanity.com/paper/2110.04375/) (2021)
- [All of the Fairness for Edge Prediction with Optimal Transport](https://mlsanity.com/paper/2010.16326/) (2020)
- [Reducing Disparate Exposure in Ranking: A Learning To Rank Approach](https://mlsanity.com/paper/1805.08716/) (2018)
- [Unbiased Graph Embedding with Biased Graph Observations](https://mlsanity.com/paper/2110.13957/) (2021)
- [End-to-end Learning for Fair Ranking Systems](https://mlsanity.com/paper/2111.10723/) (2021)
- [Correcting Exposure Bias for Link Recommendation](https://mlsanity.com/paper/2106.07041/) (2021)
- [Policy-Gradient Training of Fair and Unbiased Ranking Functions](https://mlsanity.com/paper/1911.08054/) (2019)
- [The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation](https://mlsanity.com/paper/2311.17373/) (2023)
- [FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification](https://mlsanity.com/paper/2201.11596/) (2022)
- [Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics](https://mlsanity.com/paper/2010.14531/) (2020)
- [One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes](https://mlsanity.com/paper/2406.13544/) (2024)

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

- [k-hop Fairness: Addressing Disparities in Graph Link Prediction Beyond First-Order Neighborhoods](https://mlsanity.com/paper/2603.03867/) (2026)
- [Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Study](https://mlsanity.com/paper/2608.09899/) (2026)

## Abstract (arXiv)

Link prediction is a fundamental task in graph machine learning with applications, ranging from social recommendation to knowledge graph completion. Fairness in this setting is critical, as biased predictions can exacerbate societal inequalities. Prior work adopts a dyadic definition of fairness, enforcing fairness through demographic parity between intra-group and inter-group link predictions. However, we show that this dyadic framing can obscure underlying disparities across subgroups, allowing systemic biases to go undetected. Moreover, we argue that demographic parity does not meet desired properties for fairness assessment in ranking-based tasks such as link prediction. We formalize the limitations of existing fairness evaluations and propose a framework that enables a more expressive assessment. Additionally, we propose a lightweight post-processing method combined with decoupled link predictors that effectively mitigates bias and achieves state-of-the-art fairness-utility trade-offs.