Sparse Implementation of Versatile Graph-Informed Layers
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913274929348608 |
|---|---|
| author | Della Santa, Francesco |
| author_facet | Della Santa, Francesco |
| contents | Graph Neural Networks (GNNs) have emerged as effective tools for learning tasks on graph-structured data. Recently, Graph-Informed (GI) layers were introduced to address regression tasks on graph nodes, extending their applicability beyond classic GNNs. However, existing implementations of GI layers lack efficiency due to dense memory allocation. This paper presents a sparse implementation of GI layers, leveraging the sparsity of adjacency matrices to reduce memory usage significantly. Additionally, a versatile general form of GI layers is introduced, enabling their application to subsets of graph nodes. The proposed sparse implementation improves the concrete computational efficiency and scalability of the GI layers, permitting to build deeper Graph-Informed Neural Networks (GINNs) and facilitating their scalability to larger graphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13781 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sparse Implementation of Versatile Graph-Informed Layers Della Santa, Francesco Machine Learning Numerical Analysis 68T07, 03D32 Graph Neural Networks (GNNs) have emerged as effective tools for learning tasks on graph-structured data. Recently, Graph-Informed (GI) layers were introduced to address regression tasks on graph nodes, extending their applicability beyond classic GNNs. However, existing implementations of GI layers lack efficiency due to dense memory allocation. This paper presents a sparse implementation of GI layers, leveraging the sparsity of adjacency matrices to reduce memory usage significantly. Additionally, a versatile general form of GI layers is introduced, enabling their application to subsets of graph nodes. The proposed sparse implementation improves the concrete computational efficiency and scalability of the GI layers, permitting to build deeper Graph-Informed Neural Networks (GINNs) and facilitating their scalability to larger graphs. |
| title | Sparse Implementation of Versatile Graph-Informed Layers |
| topic | Machine Learning Numerical Analysis 68T07, 03D32 |
| url | https://arxiv.org/abs/2403.13781 |