Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913264330342400 |
|---|---|
| author | de Haan, Pim Cohen, Taco Brehmer, Johann |
| author_facet | de Haan, Pim Cohen, Taco Brehmer, Johann |
| contents | The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra. We generalize this architecture into a blueprint that allows one to construct a scalable transformer architecture given any geometric (or Clifford) algebra. We study versions of this architecture for Euclidean, projective, and conformal algebras, all of which are suited to represent 3D data, and evaluate them in theory and practice. The simplest Euclidean architecture is computationally cheap, but has a smaller symmetry group and is not as sample-efficient, while the projective model is not sufficiently expressive. Both the conformal algebra and an improved version of the projective algebra define powerful, performant architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_04744 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers de Haan, Pim Cohen, Taco Brehmer, Johann Machine Learning Artificial Intelligence The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra. We generalize this architecture into a blueprint that allows one to construct a scalable transformer architecture given any geometric (or Clifford) algebra. We study versions of this architecture for Euclidean, projective, and conformal algebras, all of which are suited to represent 3D data, and evaluate them in theory and practice. The simplest Euclidean architecture is computationally cheap, but has a smaller symmetry group and is not as sample-efficient, while the projective model is not sufficiently expressive. Both the conformal algebra and an improved version of the projective algebra define powerful, performant architectures. |
| title | Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2311.04744 |