Certification and Trade-off of Multiple Fairness Criteria in Graph-based Spam Detection
Certification and Trade-off of Multiple Fairness Criteria in Graph-based Spam Detection
复制标题
DOI：
10.1145/3459637.3482325
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Kai Burkholder;Kenny Kwock;Yuesheng Xu;Jiaxin Liu;Chao Chen;Sihong Xie
中科院分区：
文献类型：
--
作者：
Kai Burkholder;Kenny Kwock;Yuesheng Xu;Jiaxin Liu;Chao Chen;Sihong Xie
垃圾评论在评论系统中很普遍，用来操纵卖家声誉和误导消费者。模式，以达到最先进的检测精度。检测可以影响大量的现实世界实体，并且尽可能平等地对待不同群体的实体是合乎道德的。然而，由于图的倾斜分布，GNN可能无法满足为不同各方设计的不同公平标准。我们建立了输入特征的线性系统和评审图的邻接矩阵，用于多个公平性标准的证明。当标准相互竞争时，我们放宽认证并设计多目标优化（MOO）算法来探索多个有效的权衡，以便在不损害另一个目标的情况下改进任何目标。利用对偶性和隐函数定理证明了该算法收敛于Pareto有效解。由于可能存在指数级的标准权衡，我们提出了一种数据驱动的随机搜索算法来近似由多个有效权衡组成的帕累托前沿。实验表明，基于公平正则化和对抗性训练，算法收敛到主导基线的解。
Spamming reviews are prevalent in review systems to manipulate seller reputation and mislead customers. patterns to achieve state-of-the-art detection accuracy. The detection can influence a large number of real-world entities and it is ethical to treat different groups of entities as equally as possible. However, due to skewed distributions of the graphs, GNN can fail to meet diverse fairness criteria designed for different parties. We formulate linear systems of the input features and the adjacency matrix of the review graphs for the certification of multiple fairness criteria. When the criteria are competing, we relax the certification and design a multi-objective optimization (MOO) algorithm to explore multiple efficient trade-offs, so that no objective can be improved without harming another objective. We prove that the algorithm converges to a Pareto efficient solution using duality and the implicit function theorem. Since there can be exponentially many trade-offs of the criteria, we propose a data-driven stochastic search algorithm to approximate Pareto fronts consisting of multiple efficient trade-offs. Experimentally, we show that the algorithms converge to solutions that dominate baselines based on fairness regularization and adversarial training.