Towards Trustworthy Hypergraph Neural Networks under Label Noise
面向标签噪声下可信赖的超图神经网络
机构 * Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院) ; University of Chinese Academy of Sciences(中国科学院大学) ; School of Mathematics and Statistics, Shandong University(山东大学数学与统计学院) ; School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院)
AI总结 本文针对标签噪声下超图节点分类问题,提出超图鲁棒框架HyperTrust,通过估计超边可信赖性及两个协同模块优化超图结构,在多数据集多噪声设置下验证了其有效性。
Comments 20 pages, 7 figures