Benutzer: Gast  Login
Titel:

When are post-hoc conceptual explanations identifiable?

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Leemann, Tobias; Kirchhof, Michael; Rong, Yao; Kasneci, Enkelejda; Kasneci, Gjergji
Abstract:
Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing. When no human concept labels are available, concept discovery methods search trained embedding spaces for interpretable concepts like object shape or color that can provide post-hoc explanations for decisions. Unlike previous work, we argue that concept discovery should be identifiable, meaning that a number of known concepts can be provably recovered to guarantee reliability o...     »
Herausgeber:
Evans, Robin J.; Shpitser, Ilya
Kongress- / Buchtitel:
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence
Band / Teilband / Volume:
216
Verlag / Institution:
PMLR
Jahr:
2023
Monat:
31 Jul--04 Aug
Seiten:
1207--1218
Serientitel:
Proceedings of Machine Learning Research
WWW:
https://proceedings.mlr.press/v216/leemann23a.html
 BibTeX