# Endowing Pre-trained Graph Models with Provable Fairness

arXiv: https://arxiv.org/abs/2402.12161 · HTML: https://mlsanity.com/paper/2402.12161/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation](https://mlsanity.com/paper/2202.03104/) (2022)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://mlsanity.com/paper/2110.08527/) (2021)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Learning Certified Individually Fair Representations](https://mlsanity.com/paper/2002.10312/) (2020)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation](https://mlsanity.com/paper/2012.07064/) (2020)
- [FARE: Provably Fair Representation Learning with Practical Certificates](https://mlsanity.com/paper/2210.07213/) (2022)
- [Center Smoothing: Certified Robustness for Networks with Structured Outputs](https://mlsanity.com/paper/2102.09701/) (2021)
- [Selective Fairness in Recommendation via Prompts](https://mlsanity.com/paper/2205.04682/) (2022)
- [Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks](https://mlsanity.com/paper/2005.04074/) (2020)

## Built on by (most cited first, 10 of 10)

- [Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient](https://mlsanity.com/paper/2405.15304/) (2024)
- [Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?](https://mlsanity.com/paper/2408.08685/) (2024)
- [A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective](https://mlsanity.com/paper/2403.16137/) (2024)
- [Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning](https://mlsanity.com/paper/2603.01385/) (2026)
- [Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective](https://mlsanity.com/paper/2501.03301/) (2025)
- [FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks](https://mlsanity.com/paper/2601.09394/) (2026)
- [Unlearning Algorithmic Biases over Graphs](https://mlsanity.com/paper/2505.14945/) (2025)
- [FairGU: Fairness-aware Graph Unlearning in Social Networks](https://mlsanity.com/paper/2601.09469/) (2026)
- [FairGC: Fairness-aware Graph Condensation](https://mlsanity.com/paper/2603.28321/) (2026)
- [ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models](https://mlsanity.com/paper/2609.33314/) (2026)

## Abstract (arXiv)

Pre-trained graph models (PGMs) aim to capture transferable inherent structural properties and apply them to different downstream tasks. Similar to pre-trained language models, PGMs also inherit biases from human society, resulting in discriminatory behavior in downstream applications. The debiasing process of existing fair methods is generally coupled with parameter optimization of GNNs. However, different downstream tasks may be associated with different sensitive attributes in reality, directly employing existing methods to improve the fairness of PGMs is inflexible and inefficient. Moreover, most of them lack a theoretical guarantee, i.e., provable lower bounds on the fairness of model predictions, which directly provides assurance in a practical scenario. To overcome these limitations, we propose a novel adapter-tuning framework that endows pre-trained graph models with provable fairness (called GraphPAR). GraphPAR freezes the parameters of PGMs and trains a parameter-efficient adapter to flexibly improve the fairness of PGMs in downstream tasks. Specifically, we design a sensitive semantic augmenter on node representations, to extend the node representations with different sensitive attribute semantics for each node. The extended representations will be used to further train an adapter, to prevent the propagation of sensitive attribute semantics from PGMs to task predictions. Furthermore, with GraphPAR, we quantify whether the fairness of each node is provable, i.e., predictions are always fair within a certain range of sensitive attribute semantics. Experimental evaluations on real-world datasets demonstrate that GraphPAR achieves state-of-the-art prediction performance and fairness on node classification task. Furthermore, based on our GraphPAR, around 90% nodes have provable fairness.