# Fairness without Demographics through Learning Graph of Gradients

arXiv: https://arxiv.org/abs/2412.03706 · HTML: https://mlsanity.com/paper/2412.03706/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 4 Dec 2024.

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

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Learning Debiased Classifier with Biased Committee](https://mlsanity.com/paper/2206.10843/) (2022)
- [AdaFair: Cumulative Fairness Adaptive Boosting](https://mlsanity.com/paper/1909.08982/) (2019)
- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [On Learning Fairness and Accuracy on Multiple Subgroups](https://mlsanity.com/paper/2210.10837/) (2022)
- [Fair Classification with Adversarial Perturbations](https://mlsanity.com/paper/2106.05964/) (2021)
- [Fairness without the sensitive attribute via Causal Variational Autoencoder](https://mlsanity.com/paper/2109.04999/) (2021)
- [Group-Aware Threshold Adaptation for Fair Classification](https://mlsanity.com/paper/2111.04271/) (2021)
- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)

## Built on by (most cited first, 4 of 4)

- [Fairness in Augmented Graph Learning: A Survey](https://mlsanity.com/paper/2504.21296/) (2025)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [Ethical Fairness in Ubiquitous Health Sensing without Known Attributes](https://mlsanity.com/paper/2603.13373/) (2026)
- [Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics](https://mlsanity.com/paper/2607.14705/) (2026)

## Abstract (arXiv)

Machine learning systems are notoriously prone to biased predictions about certain demographic groups, leading to algorithmic fairness issues. Due to privacy concerns and data quality problems, some demographic information may not be available in the training data and the complex interaction of different demographics can lead to a lot of unknown minority subpopulations, which all limit the applicability of group fairness. Many existing works on fairness without demographics assume the correlation between groups and features. However, we argue that the model gradients are also valuable for fairness without demographics. In this paper, we show that the correlation between gradients and groups can help identify and improve group fairness. With an adversarial weighting architecture, we construct a graph where samples with similar gradients are connected and learn the weights of different samples from it. Unlike the surrogate grouping methods that cluster groups from features and labels as proxy sensitive attribute, our method leverages the graph structure as a soft grouping mechanism, which is much more robust to noises. The results show that our method is robust to noise and can improve fairness significantly without decreasing the overall accuracy too much.