# FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization

arXiv: https://arxiv.org/abs/2403.12474 · HTML: https://mlsanity.com/paper/2403.12474/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [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)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [Molecular graph generation with Graph Neural Networks](https://mlsanity.com/paper/2012.07397/) (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)
- [All of the Fairness for Edge Prediction with Optimal Transport](https://mlsanity.com/paper/2010.16326/) (2020)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [Unbiased Graph Embedding with Biased Graph Observations](https://mlsanity.com/paper/2110.13957/) (2021)
- [Fair Node Representation Learning via Adaptive Data Augmentation](https://mlsanity.com/paper/2201.08549/) (2022)
- [Linking Bank Clients using Graph Neural Networks Powered by Rich Transactional Data](https://mlsanity.com/paper/2001.08427/) (2020)

## Built on by (most cited first, 20 of 20)

- [FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning](https://mlsanity.com/paper/2412.10669/) (2024)
- [Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks](https://mlsanity.com/paper/2408.12875/) (2024)
- [DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning](https://mlsanity.com/paper/2508.12244/) (2025)
- [FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks](https://mlsanity.com/paper/2601.09394/) (2026)
- [Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing](https://mlsanity.com/paper/2505.09702/) (2025)
- [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)
- [Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributes](https://mlsanity.com/paper/2412.09947/) (2024)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [FairGSE: Fairness-Aware Graph Neural Network without High False Positive Rates](https://mlsanity.com/paper/2511.12132/) (2025)
- [Debiasing Graph Representation Learning based on Information Bottleneck](https://mlsanity.com/paper/2409.01367/) (2024)
- [Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation](https://mlsanity.com/paper/2412.00382/) (2024)
- [Trustworthy GNNs with LLMs: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2502.08353/) (2025)
- [Learning Fair Graph Representations with Multi-view Information Bottleneck](https://mlsanity.com/paper/2510.25096/) (2025)
- [A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective](https://mlsanity.com/paper/2510.23507/) (2025)
- [Mitigating Bias in Graph Hyperdimensional Computing](https://mlsanity.com/paper/2512.07433/) (2025)
- [FairGC: Fairness-aware Graph Condensation](https://mlsanity.com/paper/2603.28321/) (2026)
- [Geometrical fairness in graph neural networks](https://mlsanity.com/paper/2606.17684/) (2026)
- [Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics](https://mlsanity.com/paper/2607.14705/) (2026)
- [Subgraph Filtering for Fair Graph Neural Networks](https://mlsanity.com/paper/2608.26437/) (2026)

## Abstract (arXiv)

Despite the remarkable success of graph neural networks (GNNs) in modeling graph-structured data, like other machine learning models, GNNs are also susceptible to making biased predictions based on sensitive attributes, such as race and gender. For fairness consideration, recent state-of-the-art (SOTA) methods propose to filter out sensitive information from inputs or representations, e.g., edge dropping or feature masking. However, we argue that such filtering-based strategies may also filter out some non-sensitive feature information, leading to a sub-optimal trade-off between predictive performance and fairness. To address this issue, we unveil an innovative neutralization-based paradigm, where additional Fairness-facilitating Features (F3) are incorporated into node features or representations before message passing. The F3 are expected to statistically neutralize the sensitive bias in node representations and provide additional nonsensitive information. We also provide theoretical explanations for our rationale, concluding that F3 can be realized by emphasizing the features of each node's heterogeneous neighbors (neighbors with different sensitive attributes). We name our method as FairSIN, and present three implementation variants from both data-centric and model-centric perspectives. Experimental results on five benchmark datasets with three different GNN backbones show that FairSIN significantly improves fairness metrics while maintaining high prediction accuracies.