提出FairGSE框架，在提升公平性的同时显著降低误报率。
FairGSE: Fairness-Aware Graph Neural Network without High False Positive Rates
- 通过最大化二维结构熵优化图神经网络的公平性
- 在真实数据集上使误报率降低39%
- 适合高风险场景下需兼顾公平与低误报的应用
图神经网络（GNN）因其高效的消息聚合能力成为图表示学习的主流范式，但这一优势也放大了图拓扑中的固有偏差，引发公平性问题。现有公平性增强的GNN在统计均等性和机会均等性等指标上表现良好，且准确率损失可控，但其对负样本预测能力不足，导致误报率（FPR）过高，在高风险场景中产生负面影响。为此，我们主张在提升公平性时应精细校准分类性能，而非仅控制准确率下降。本文提出基于结构熵的公平图神经网络（FairGSE），通过最大化二维结构熵（2D-SE）实现公平性提升，同时避免忽略负样本预测。实验表明，FairGSE在多个真实世界数据集上相较当前最优公平性GNN，误报率降低39%，公平性提升相当。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have emerged as the mainstream paradigm for graph representation learning due to their effective message aggregation. However, this advantage also amplifies biases inherent in graph topology, raising fairness concerns. Existing fairness-aware GNNs provide satisfactory performance on fairness metrics such as Statistical Parity and Equal Opportunity while maintaining acceptable accuracy trade-offs. Unfortunately, we observe that this pursuit of fairness metrics neglects the GNN's ability to predict negative labels, which renders their predictions with extremely high False Positive Rates (FPR), resulting in negative effects in high-risk scenarios. To this end, we advocate that classification performance should be carefully calibrated while improving fairness, rather than simply constraining accuracy loss. Furthermore, we propose Fair GNN via Structural Entropy (\textbf{FairGSE}), a novel framework that maximizes two-dimensional structural entropy (2D-SE) to improve fairness without neglecting false positives. Experiments on several real-world datasets show FairGSE reduces FPR by 39\% vs. state-of-the-art fairness-aware GNNs, with comparable fairness improvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。