SRBGCN: Tangent space-Free Lorentz Transformations for Graph Feature Learning.
Mostafa, Abdelrahman; Peng, Wei; Zhao, Guoying
BMVA Press
Mostafa, A., Peng, W. & Zhao, G. (2023). SRBGCN: Tangent space-Free Lorentz Transformations for Graph Feature Learning. In 34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023. http://proceedings.bmvc2023.org/669/
https://rightsstatements.org/vocab/InC/1.0/
© 2023. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
https://rightsstatements.org/vocab/InC/1.0/
© 2023. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202401231410
https://urn.fi/URN:NBN:fi:oulu-202401231410
Tiivistelmä
Abstract
Hyperbolic graph convolutional networks have been successfully applied to represent complex graph data structures. However, optimization on Riemannian manifolds is nontrivial thus most of the existing hyperbolic networks build the network operations on the tangent space of the manifold, which is a Euclidean local approximation. This distorts the learnt features and limits the representation capacity of the network. In this work, we introduce a fully hyperbolic graph convolutional network (GCN), referred to as SRBGCN, which performs neural computations such as feature transformation and aggregation directly on the manifold, using manifold-preserving Lorentz transformations that include spatial rotation (SR) and boost (B) operations. Experiments conducted on static graph datasets for node classification and link prediction tasks validate the performance of the proposed method.
Hyperbolic graph convolutional networks have been successfully applied to represent complex graph data structures. However, optimization on Riemannian manifolds is nontrivial thus most of the existing hyperbolic networks build the network operations on the tangent space of the manifold, which is a Euclidean local approximation. This distorts the learnt features and limits the representation capacity of the network. In this work, we introduce a fully hyperbolic graph convolutional network (GCN), referred to as SRBGCN, which performs neural computations such as feature transformation and aggregation directly on the manifold, using manifold-preserving Lorentz transformations that include spatial rotation (SR) and boost (B) operations. Experiments conducted on static graph datasets for node classification and link prediction tasks validate the performance of the proposed method.
Kokoelmat
- Avoin saatavuus [38865]