Difference between revisions of "Publications/veyrin-forrer.22.egc"
From LRDE
Line 12: | Line 12: | ||
| lrdenewsdate = 2022-03-24 |
| lrdenewsdate = 2022-03-24 |
||
| abstract = While existing GNN's explanation methods explain the decision by studying the output layer, we propose a method that analyzes the hidden layers to identify the neurons that are co-activated for a class. We associate to them a graph. |
| abstract = While existing GNN's explanation methods explain the decision by studying the output layer, we propose a method that analyzes the hidden layers to identify the neurons that are co-activated for a class. We associate to them a graph. |
||
+ | | nodoi = |
||
| type = inproceedings |
| type = inproceedings |
||
| id = veyrin-forrer.22.egc |
| id = veyrin-forrer.22.egc |
||
Line 32: | Line 33: | ||
that analyzes the hidden layers to identify the neurons |
that analyzes the hidden layers to identify the neurons |
||
that are co-activated for a class. We associate to them a |
that are co-activated for a class. We associate to them a |
||
− | graph.<nowiki>}</nowiki> |
+ | graph.<nowiki>}</nowiki>, |
+ | nodoi = <nowiki>{</nowiki><nowiki>}</nowiki> |
||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Latest revision as of 19:08, 7 April 2023
- Authors
- Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet
- Where
- Extraction et Gestion des Connaissances, EGC 2022Blois, France, 24 au 28 janvier 2022
- Type
- inproceedings
- Keywords
- IA
- Date
- 2022-03-24
Abstract
While existing GNN's explanation methods explain the decision by studying the output layer, we propose a method that analyzes the hidden layers to identify the neurons that are co-activated for a class. We associate to them a graph.
Bibtex (lrde.bib)
@InProceedings{ veyrin-forrer.22.egc, author = {Luca {Veyrin-Forrer} and Ataollah Kamal and Stefan Duffner and Marc Plantevit and C\'eline Robardet}, title = {Qu'est-ce que mon {GNN} capture vraiment ? {E}xploration des repr\'esentations internes d'un {GNN}}, booktitle = {Extraction et Gestion des Connaissances, {EGC} 2022, Blois, France, 24 au 28 janvier 2022}, pages = {159--170}, year = {2022}, month = jan, opturl = {http://editions-rnti.fr/?inprocid=1002725}, note = {In French, Best paper award}, category = {national}, abstract = {While existing GNN's explanation methods explain the decision by studying the output layer, we propose a method that analyzes the hidden layers to identify the neurons that are co-activated for a class. We associate to them a graph.}, nodoi = {} }