Training-free Graph Neural Networks and the Power of Labels as Features
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909287282900992 |
|---|---|
| author | Sato, Ryoma |
| author_facet | Sato, Ryoma |
| contents | We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19288 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Training-free Graph Neural Networks and the Power of Labels as Features Sato, Ryoma Machine Learning Artificial Intelligence We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs. |
| title | Training-free Graph Neural Networks and the Power of Labels as Features |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.19288 |