Edge-Wise Graph-Instructed Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909450824056832 |
|---|---|
| author | Della Santa, Francesco Mastropietro, Antonio Pieraccini, Sandra Vaccarino, Francesco |
| author_facet | Della Santa, Francesco Mastropietro, Antonio Pieraccini, Sandra Vaccarino, Francesco |
| contents | The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural networks. In this work, we discuss the limitations of the Graph-Instructed (GI) layer, and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages of the EWGI layer and we provide numerical evidence that EWGINNs perform better than GINNs over some graph-structured input data, like the ones inferred from the Barabasi-Albert graph, and improve the training regularization on graphs with chaotic connectivity, like the ones inferred from the Erdos-Renyi graph. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08023 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Edge-Wise Graph-Instructed Neural Networks Della Santa, Francesco Mastropietro, Antonio Pieraccini, Sandra Vaccarino, Francesco Machine Learning Artificial Intelligence Numerical Analysis 05C21, 65D15, 68T07, 90C35 The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural networks. In this work, we discuss the limitations of the Graph-Instructed (GI) layer, and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages of the EWGI layer and we provide numerical evidence that EWGINNs perform better than GINNs over some graph-structured input data, like the ones inferred from the Barabasi-Albert graph, and improve the training regularization on graphs with chaotic connectivity, like the ones inferred from the Erdos-Renyi graph. |
| title | Edge-Wise Graph-Instructed Neural Networks |
| topic | Machine Learning Artificial Intelligence Numerical Analysis 05C21, 65D15, 68T07, 90C35 |
| url | https://arxiv.org/abs/2409.08023 |