Variational Graph Convolutional Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911035072446464 |
|---|---|
| author | Oleksiienko, Illia Kanniainen, Juho Iosifidis, Alexandros |
| author_facet | Oleksiienko, Illia Kanniainen, Juho Iosifidis, Alexandros |
| contents | Estimation of model uncertainty can help improve the explainability of Graph Convolutional Networks and the accuracy of the models at the same time. Uncertainty can also be used in critical applications to verify the results of the model by an expert or additional models. In this paper, we propose Variational Neural Network versions of spatial and spatio-temporal Graph Convolutional Networks. We estimate uncertainty in both outputs and layer-wise attentions of the models, which has the potential for improving model explainability. We showcase the benefits of these models in the social trading analysis and the skeleton-based human action recognition tasks on the Finnish board membership, NTU-60, NTU-120 and Kinetics datasets, where we show improvement in model accuracy in addition to estimated model uncertainties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Variational Graph Convolutional Neural Networks Oleksiienko, Illia Kanniainen, Juho Iosifidis, Alexandros Machine Learning Estimation of model uncertainty can help improve the explainability of Graph Convolutional Networks and the accuracy of the models at the same time. Uncertainty can also be used in critical applications to verify the results of the model by an expert or additional models. In this paper, we propose Variational Neural Network versions of spatial and spatio-temporal Graph Convolutional Networks. We estimate uncertainty in both outputs and layer-wise attentions of the models, which has the potential for improving model explainability. We showcase the benefits of these models in the social trading analysis and the skeleton-based human action recognition tasks on the Finnish board membership, NTU-60, NTU-120 and Kinetics datasets, where we show improvement in model accuracy in addition to estimated model uncertainties. |
| title | Variational Graph Convolutional Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.01699 |