提出多视图信息瓶颈框架，让图神经网络更公平地学习节点表示。
Learning Fair Graph Representations with Multi-view Information Bottleneck
- 将图分解为特征、结构和传播三视图，分别处理不同来源的偏见。
- 通过对比学习最大化跨视图互信息，提升表示质量并抑制偏见传播。
- 适合关注模型公平性且使用图数据的研究者，尤其在社会关系分析中适用。
图神经网络在关系数据上表现优异，但会放大训练数据中的偏见，将歧视性属性和结构不平衡传播至不公平结果。现有公平性方法多将偏见视为单一来源，忽略属性与结构的差异化影响，导致公平性与性能权衡不佳。为此，本文提出 FairMIB，一种多视图信息瓶颈框架，将图分解为特征、结构和扩散三个视图，以缓解复杂偏见。该方法采用对比学习最大化跨视图互信息，实现无偏表示学习；同时引入多视角条件信息瓶颈目标，通过最小化与敏感属性的互信息，在任务性能与公平性间取得平衡。此外，扩散视图中引入逆概率加权（IPW）邻接修正，减少消息传递过程中的偏见传播。在五个真实世界基准数据集上的实验表明，FairMIB 在公平性和实用性指标上均达到当前最优水平。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) excel on relational data by passing messages over node features and structure, but they can amplify training data biases, propagating discriminatory attributes and structural imbalances into unfair outcomes. Many fairness methods treat bias as a single source, ignoring distinct attribute and structure effects and leading to suboptimal fairness and utility trade-offs. To overcome this challenge, we propose FairMIB, a multi-view information bottleneck framework designed to decompose graphs into feature, structural, and diffusion views for mitigating complexity biases in GNNs. Especially, the proposed FairMIB employs contrastive learning to maximize cross-view mutual information for bias-free representation learning. It further integrates multi-perspective conditional information bottleneck objectives to balance task utility and fairness by minimizing mutual information with sensitive attributes. Additionally, FairMIB introduces an inverse probability-weighted (IPW) adjacency correction in the diffusion view, which reduces the spread of bias propagation during message passing. Experiments on five real-world benchmark datasets demonstrate that FairMIB achieves state-of-the-art performance across both utility and fairness metrics.
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。