Difference between revisions of "Publications/veyrin-forrer.22.egc"

From LRDE

 
(2 intermediate revisions by the same user not shown)
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 24: Line 25:
 
pages = <nowiki>{</nowiki>159--170<nowiki>}</nowiki>,
 
pages = <nowiki>{</nowiki>159--170<nowiki>}</nowiki>,
 
year = <nowiki>{</nowiki>2022<nowiki>}</nowiki>,
 
year = <nowiki>{</nowiki>2022<nowiki>}</nowiki>,
  +
month = jan,
 
opturl = <nowiki>{</nowiki>http://editions-rnti.fr/?inprocid=1002725<nowiki>}</nowiki>,
 
opturl = <nowiki>{</nowiki>http://editions-rnti.fr/?inprocid=1002725<nowiki>}</nowiki>,
 
note = <nowiki>{</nowiki>In French, Best paper award<nowiki>}</nowiki>,
 
note = <nowiki>{</nowiki>In French, Best paper award<nowiki>}</nowiki>,
Line 31: 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

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		= {}
}