Graph Geometry Interaction Learning
arXiv:2010.12135
Abstract
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.
arXiv commentPublished at Conference NeurIPS 2020
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Hierarchical structure and the prediction of missing links in networks
- Hierarchical Organization in Complex Networks
- Fast Graph Representation Learning with PyTorch Geometric
- Simplifying Graph Convolutional Networks
- Hyperbolic Graph Convolutional Neural Networks
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
- Hyperbolic Graph Neural Networks