Multi-View Graph Learning with Graph-Tuple
多视图图学习与图元组
机构 * Department of Applied Mathematics and Statistics(应用数学与统计学系) ; Johns Hopkins University(约翰霍普金斯大学) ; Flatiron Institute(Flatiron研究所)
AI总结 本文提出多视图图元组框架,通过异质信息传递架构提升图神经网络的表现力,应用于分子属性预测和宇宙学参数推断,展现其在处理密集图数据中的优势。
Comments Accepted as a poster at the TAG-DS 2025 Workshop (Topology, Algebra, and Geometry in Data Science). OpenReview: https://openreview.net/forum?id=s4ezAuj5xM