Equivariance by Local Canonicalization: A Matter of Representation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914068414070784 |
|---|---|
| author | Gerhartz, Gerrit Lippmann, Peter Hamprecht, Fred A. |
| author_facet | Gerhartz, Gerrit Lippmann, Peter Hamprecht, Fred A. |
| contents | Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers existing tensor field networks into the more efficient local canonicalization paradigm, preserving equivariance while significantly improving the runtime. Within this framework, we systematically compare different equivariant representations in terms of theoretical complexity, empirical runtime, and predictive accuracy. We publish the tensor_frames package, a PyTorchGeometric based implementation for local canonicalization, that enables straightforward integration of equivariance into any standard message passing neural network. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26499 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Equivariance by Local Canonicalization: A Matter of Representation Gerhartz, Gerrit Lippmann, Peter Hamprecht, Fred A. Machine Learning Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers existing tensor field networks into the more efficient local canonicalization paradigm, preserving equivariance while significantly improving the runtime. Within this framework, we systematically compare different equivariant representations in terms of theoretical complexity, empirical runtime, and predictive accuracy. We publish the tensor_frames package, a PyTorchGeometric based implementation for local canonicalization, that enables straightforward integration of equivariance into any standard message passing neural network. |
| title | Equivariance by Local Canonicalization: A Matter of Representation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.26499 |