Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2410.20516 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912089417711616 |
|---|---|
| author | Balla, Julia Mishra-Sharma, Siddharth Cuesta-Lazaro, Carolina Jaakkola, Tommi Smidt, Tess |
| author_facet | Balla, Julia Mishra-Sharma, Siddharth Cuesta-Lazaro, Carolina Jaakkola, Tommi Smidt, Tess |
| contents | Efficiently processing structured point cloud data while preserving multiscale information is a key challenge across domains, from graphics to atomistic modeling. Using a curated dataset of simulated galaxy positions and properties, represented as point clouds, we benchmark the ability of graph neural networks to simultaneously capture local clustering environments and long-range correlations. Given the homogeneous and isotropic nature of the Universe, the data exhibits a high degree of symmetry. We therefore focus on evaluating the performance of Euclidean symmetry-preserving ($E(3)$-equivariant) graph neural networks, showing that they can outperform non-equivariant counterparts and domain-specific information extraction techniques in downstream performance as well as simulation-efficiency. However, we find that current architectures fail to capture information from long-range correlations as effectively as domain-specific baselines, motivating future work on architectures better suited for extracting long-range information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20516 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing Balla, Julia Mishra-Sharma, Siddharth Cuesta-Lazaro, Carolina Jaakkola, Tommi Smidt, Tess Machine Learning Instrumentation and Methods for Astrophysics Efficiently processing structured point cloud data while preserving multiscale information is a key challenge across domains, from graphics to atomistic modeling. Using a curated dataset of simulated galaxy positions and properties, represented as point clouds, we benchmark the ability of graph neural networks to simultaneously capture local clustering environments and long-range correlations. Given the homogeneous and isotropic nature of the Universe, the data exhibits a high degree of symmetry. We therefore focus on evaluating the performance of Euclidean symmetry-preserving ($E(3)$-equivariant) graph neural networks, showing that they can outperform non-equivariant counterparts and domain-specific information extraction techniques in downstream performance as well as simulation-efficiency. However, we find that current architectures fail to capture information from long-range correlations as effectively as domain-specific baselines, motivating future work on architectures better suited for extracting long-range information. |
| title | A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing |
| topic | Machine Learning Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2410.20516 |