Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics

• URL: http://arxiv.org/abs/2607.14705v1
• Date: Thu, 16 Jul 2026 08:06:39 GMT
• Title: Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics
• Abstract summary: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups.<n>To mitigate this bias, we propose Gradient-to-Fairness (Grad2Fair), a gradient-guided approach for group fairness without demographics.
• Score: 44.98478567813759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted demographics as proxies to enforce fairness constraints. However, predicted demographics may be inaccurate, resulting in the failure to improve fairness. In this work, we investigate the problem of graph fairness without demographic information and avoid the utilization of predicted demographics. Motivated by our observation that the gradient distributions of misclassified nodes implicitly encode demographic information, we first propose GradDist, a gradient-based metric that quantifies bias by measuring the distance between local modes within these distributions. To mitigate this bias, we propose Gradient-to-Fairness (Grad2Fair), a gradient-guided approach for group fairness without demographics. Due to the potential demographics in gradients, Grad2Fair directly leverages gradients to debias and eliminates demographic prediction, thereby enabling stable fairness performance. Experiments on several real-world datasets demonstrate the effectiveness of Grad2Fair, as evidenced by superior performance over baselines in most cases. Our code is available at https://github.com/ZzoomD/Grad2Fair.

Related papers

• Bias Mitigation in Face Recognition via Demographic-based Supervised Contrastive Learning [4.060167104955954]
  Face recognition systems have been shown to be biased toward certain demographic groups by exhibiting different error rates across gender, age, or ethnicity.<n>We propose the Demographic-based Supervised Contrastive loss (DeSCon) for face recognition, which relies on a well-designed composition of training batches and demographic-aware pair selection.
  arXiv  Detail & Related papers  (2026-08-13T08:51:33Z)
• FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection [60.2868121662026]
  Existing fairness-enhanced detectors often suffer from suboptimal generalization to unseen manipulations and fairness across demographic groups.<n>We construct a novel demographically balanced FDD benchmark to train and evaluate the fairness of detectors under both balanced and imbalanced population scenarios.<n>We also introduce a novel expression and demographic perceptual vision-language model, termed FairForensics, for generalizable fair deepfake detection.
  arXiv  Detail & Related papers  (2026-08-03T03:51:14Z)
• Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing [11.879507789144062]
  Graph unlearning is a crucial approach for protecting user privacy by erasing the influence of user data on trained graph models.<n>Recent developments in graph unlearning methods have primarily focused on maintaining model prediction performance while removing user information.<n>We propose a fair graph unlearning method, FGU, to ensure fairness while maintaining privacy and accuracy.
  arXiv  Detail & Related papers  (2025-05-14T18:04:02Z)
• Fairness without Demographics through Learning Graph of Gradients [22.260763111752805]
  We show that the correlation between gradients and groups can help identify and improve group fairness.<n>Our method is robust to noise and can improve fairness significantly without decreasing the overall accuracy too much.
  arXiv  Detail & Related papers  (2024-12-04T20:35:50Z)
• Towards Harmless Rawlsian Fairness Regardless of Demographic Prior [57.30787578956235]
  We explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set. We propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses.
  arXiv  Detail & Related papers  (2024-11-04T12:40:34Z)
• Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information [50.29934517930506]
  DAFair is a novel approach to address social bias in language models. We leverage prototypical demographic texts and incorporate a regularization term during the fine-tuning process to mitigate bias.
  arXiv  Detail & Related papers  (2024-03-14T15:58:36Z)
• Migrate Demographic Group For Fair GNNs [23.096452685455134]
  Graph Neural networks (GNNs) have been applied in many scenarios due to the superior performance of graph learning. FairMigration is composed of two training stages. In the first stage, the GNNs are initially optimized by personalized self-supervised learning. In the second stage, the new demographic groups are frozen and supervised learning is carried out under the constraints of new demographic groups and adversarial training.
  arXiv  Detail & Related papers  (2023-06-07T07:37:01Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning [14.664485680918725]
  We propose a biased edge dropout algorithm (FairDrop) to counter-act homophily and improve fairness in graph representation learning. FairDrop can be plugged in easily on many existing algorithms, is efficient, adaptable, and can be combined with other fairness-inducing solutions. We prove that the proposed algorithm can successfully improve the fairness of all models up to a small or negligible drop in accuracy.
  arXiv  Detail & Related papers  (2021-04-29T08:59:36Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.