Hyperbolic Graph Neural Networks
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)(2019)
摘要
Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps. We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry. In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets.
更多查看译文
关键词
artificial intelligence (ai),artificial intelligence,machine learning,riemannian manifold,hyperbolic geometry,riemannian manifolds,data structures,structured data,data structure
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络