Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
arXiv:2106.04941
Abstract
Learning faithful graph representations as sets of vertex embeddings has become a fundamental intermediary step in a wide range of machine learning applications. We propose the systematic use of symmetric spaces in representation learning, a class encompassing many of the previously used embedding targets. This enables us to introduce a new method, the use of Finsler metrics integrated in a Riemannian optimization scheme, that better adapts to dissimilar structures in the graph. We develop a tool to analyze the embeddings and infer structural properties of the data sets. For implementation, we choose Siegel spaces, a versatile family of symmetric spaces. Our approach outperforms competitive baselines for graph reconstruction tasks on various synthetic and real-world datasets. We further demonstrate its applicability on two downstream tasks, recommender systems and node classification.
28 pages. Accepted at ICML 2021
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Hyperbolic Geometry of Complex Networks
- Curvature and temperature of complex networks
- A Riemannian Network for SPD Matrix Learning
- Spherical Text Embedding
- Geoopt: Riemannian Optimization in PyTorch
- From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
- DeepSphere: a graph-based spherical CNN