Influential Examples

Label-Free Explainability for Unsupervised Models
We extend existing feature and example importance methods to unsupervised learning.
Jonathan Crabbé, Mihaela van der Schaar
PDF Cite Code Project Project Video
Label-Free Explainability for Unsupervised Models
Explaining Latent Representations with a Corpus of Examples
We introduce SimplEx, a case-based reasoning explanation method that permits to decompose latent representations with a corpus of example.
Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar
PDF Cite Code Project Video
Explaining Latent Representations with a Corpus of Examples