论文标题
图几何相互作用学习
Graph Geometry Interaction Learning
论文作者
论文摘要
尽管已经开发出许多方法将图形嵌入到欧几里得或双曲线空间中，但它们并未完全利用图中可用的信息，或者缺乏对固有的复杂图几何形状进行建模的灵活性。为了利用欧几里得和双曲线几何形状的强度，我们开发了一种新颖的几何相互作用学习（GIL）方法，用于图形，一种非常适合和有效的替代方案，用于学习图中丰富的几何特性。吉尔（Gil）捕获了一个更具信息性的内部结构特征，其尺寸较低，同时保持每个空间的保形不变性。此外，我们的方法赋予了每个节点通过灵活的双特征交互学习和概率组装机制来确定每个几何空间的重要性的自由。关于节点分类和链接预测任务的五个基准数据集提供了有希望的实验结果。
While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. GIL captures a more informative internal structural features with low dimensions while maintaining conformal invariance of each space. Furthermore, our method endows each node the freedom to determine the importance of each geometry space via a flexible dual feature interaction learning and probability assembling mechanism. Promising experimental results are presented for five benchmark datasets on node classification and link prediction tasks.
