What Does my GNN Really Capture? On Exploring Internal GNN Representations
From LRDE
- Authors
- Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet
- Where
- International Joint Conference on Artificial Intelligence 2022
- Type
- inproceedings
- Publisher
- ijcai.org
- Keywords
- IA
- Date
- 2022-07-23
Abstract
GNNs are efficient for classifying graphs but their internal workings is opaque which limits their field of application. Existing methods for explaining GNN focus on disclosing the relationships between input graphs and the model's decision. In contrary, the method we propose isolates internal features, hidden in the network layerswhich are automatically identified by the GNN to classify graphs. We show that this method makes it possible to know the parts of the input graphs used by GNN with much less bias than the SOTA methods and therefore to provide confidence in the decision process.
Bibtex (lrde.bib)
@InProceedings{ veyrin-forrer.22.ijcai,
title = {What Does my {GNN} Really Capture? {O}n Exploring Internal
GNN Representations},
author = {Luca Veyrin-Forrer and Ataollah Kamal and Stefan Duffner
and Marc Plantevit and C\'eline Robardet},
booktitle = {International Joint Conference on Artificial Intelligence
2022},
year = {2022},
month = jul,
hal_id = {hal-03700710},
pages = {747--752},
abstract = {GNNs are efficient for classifying graphs but their
internal workings is opaque which limits their field of
application. Existing methods for explaining GNN focus on
disclosing the relationships between input graphs and the
model's decision. In contrary, the method we propose
isolates internal features, hidden in the network layers,
which are automatically identified by the GNN to classify
graphs. We show that this method makes it possible to know
the parts of the input graphs used by GNN with much less
bias than the SOTA methods and therefore to provide
confidence in the decision process.},
publisher = {ijcai.org},
doi = {https://doi.org/10.24963/ijcai.2022/105}
}