Fair Graph Distillation
As graph neural networks (GNNs) struggle with large-scale graphs due to high computational demands, data distillation for graph data promises to alleviate this issue by distilling a large real graph into a smaller distilled graph while maintaining comparable prediction performance for GNNs trained on both graphs. However, we observe that GNNs trained on distilled graphs may exhibit more severe group fairness problems than those trained on real graphs. Motivated by this observation, we propose \textit{fair graph distillation} (\Algnameabbr), an approach for generating small distilled \textit{fair and informative} graphs based on the graph distillation method. The challenge lies in the deficiency of sensitive attributes for nodes in the distilled graph, making most debiasing methods (e.g., regularization and adversarial debiasing) intractable for distilled graphs. We develop a simple yet effective bias metric, called coherence, for distilled graphs. Based on the proposed coherence metric, we introduce a framework for fair graph distillation using a bi-level optimization algorithm. Extensive experiments demonstrate that the proposed algorithm can achieve better prediction performance-fairness trade-offs across various datasets and GNN architectures.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation
Graph Neural Networks (GNNs) have demonstrated strong performance in graph representation learning across various real-world applications. However, they often produce biased predictions caused by sensitive attributes, su…
FairnessGraph Representation LearningKnowledge DistillationRepresentation LearningFairness without Demographics through Knowledge Distillation
Most of existing work on fairness assumes available demographic information in the training set. In practice, due to legal or privacy concerns, when demographic information is not available in the training set, it is cru…
FairnessKnowledge DistillationThe Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
Graph neural networks (GNNs) are being increasingly used in many high-stakes tasks, and as a result, there is growing attention on their fairness recently. GNNs have been shown to be unfair as they tend to make discrimin…
FairnessKnowledge DistillationRELIANT: Fair Knowledge Distillation for Graph Neural Networks
Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationall…
FairnessGraph LearningKnowledge DistillationWhat is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias
Knowledge Distillation is a commonly used Deep Neural Network (DNN) compression method, which often maintains overall generalization performance. However, we show that even for balanced image classification datasets, suc…
Age/UnbiasedFairnessGender Bias Detectionimage-classification+6