Skip to content
Conference Open access

Towards Fair Graph Learning Without Demographic Supervision

Sep 2026 · Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence · 4 citations · 46 references

TL;DR

Demographic-Independent Fair Graph Learning mitigates group unfairness by minimizing disparities in individual treatment across implicitly identified subgroups, thereby enforcing fairness without requiring explicit demographic information.

Abstract

Graph Neural Networks (GNNs) have demonstrated strong predictive performance across a wide range of applications. However, their increasing deployment has raised critical fairness concerns, as these models can inherit and amplify existing biases. Most existing fairness approaches rely on explicit demographic information, either directly available or inferred, to measure and mitigate bias. In real-world settings, however, such information is often unavailable or legally prohibited to infer due to privacy concerns, legal restrictions, or regulatory constraints, which substantially limits the applicability of these methods. To address this challenge, we propose Demographic-Independent Fair Graph Learning (DIFGL), a novel framework for fair graph learning without demographic supervision. DIFGL mitigates group unfairness by minimizing disparities in individual treatment across implicitly identified subgroups, thereby enforcing fairness without requiring explicit demographic information. Extensive experiments on benchmark datasets demonstrate that DIFGL achieves significant improvements in fairness while maintaining competitive predictive performance.

Read PDF

Similar papers

#graph neural networks Open access Sep 2026

Fair Graph Learning Needs Expressiveness: Rethinking Fairness from the Spectral Perspective

It is formally proved that GNN architectures lacking spectral expressiveness impose strict constraints on the representation space, so that harmful linear correlations between sensitive attributes and target prediction logits are preserved whenever a low-expressive backbone is paired with a debiasing operator acting wi...

Ming-Qi Yang, Zhao-Yu Liu · 0 citations
Conference Open access Sep 2026

Disentangled Graph-Enhanced Large Language Models for Fair Learning

FairGEnt, a disentangled graph-enhanced large language model for fair graph learning, separates sensitive-related and sensitive-invariant factors in both graph and textual representations to mitigate bias while preserving task-relevant information, and further aligns the two modalities through a fairness-aware integrat...

Zhi-Peng Yin, Zi-Chong Wang, Zhong Chen et al. · 5 citations
#machine learning Preprint Oct 2026

FairProp: Fair Node Representation Learning via Differentiable Propagation Layers

Graph neural networks (GNNs) are the standard tool for node representation learning and are increasingly used in high-stakes settings. Their message-passing backbone, however, can amplify topological bias, raising fairness concerns. We study group fairness at the level of downstream predictions for node classification,...

E. Kariotakis, Aritra Konar · 0 citations
Review Aug 2026

Fairness-Aware Network Embeddings: Methods, Applications, and Challenges

This survey presents a comprehensive overview of fairness-aware network embeddings for complex networks and proposes a taxonomy that categorizes existing methods along three main complementary dimensions: underlying embedding approach, fairness intervention strategy, and fairness objective criterion.

E. Has, Harshit Yadav, Gaurav Dixit et al. · 1 citation
Preprint Aug 2026

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization

This work identifies routing-induced bias, a failure mode in which subgroup imbalance drives the gating network to route subgroups onto a few experts, and proposes an end-to-end Mixture-of-Experts (MoE) framework that corrects it and improves fairness while maintaining competitive predictive performance.

Sunhee Hwang · 0 citations
#machine learning Preprint Oct 2026

Debias Anything: Fairness with Diversity without Supervision in Diffusion Models

Although diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their generation process post-training w.r.t. some sensitive attribute usually relies on classifier guidance or explicit text extra-conditioning, but this reduces methods'appli...

Théau d'Audiffret, M. Vladimirova, Jean-Yves Franceschi · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.