Fair Graph Neural Network with Supervised Contrastive Regularization - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Fair Graph Neural Network with Supervised Contrastive Regularization

Résumé

In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances the Counterfactual Augmented Fair Graph Neural Network Framework (CAF). Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness. Experimental validation on three real datasets demonstrates the superiority of our proposed model over CAF and several other existing graph-based learning methods.
Fichier principal
Vignette du fichier
paperMFJM.pdf (1.8 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04537254 , version 1 (08-04-2024)

Licence

Domaine public

Identifiants

  • HAL Id : hal-04537254 , version 1

Citer

Mahdi Tavassoli Kejani, Fadi Dornaika, Jean-Michel Loubes. Fair Graph Neural Network with Supervised Contrastive Regularization. 2024. ⟨hal-04537254⟩
34 Consultations
17 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More