USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
Unsupervised/self-supervised graph neural networks (GNN) are vulnerable to inherent randomness in the input graph data which greatly affects the performance of the model in downstream tasks. In this paper, we alleviate the interference of graph randomness and learn appropriate representations of nod...
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Article |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2302.05889 http://arxiv.org/abs/2302.05889 |
| Tags: |
Pas de tags, Soyez le premier à ajouter un tag!
|