Résumé
Non-linear dimensionality reduction techniques, such as tSNE, are widely used to visualize and analyze high-dimensional datasets. While non-linear projections can be of high quality, it is hard, or even impossible, to interpret the dimensions of the obtained embeddings. This paper adapts LIME to locally explain t-SNE embeddings. More precisely, the sampling and black-box-querying steps of LIME are modified so that they can be used to explain t-SNE locally. The result of the proposal is to provide, for a particular instance x and a particular t-SNE embedding Y, an interpretable model that locally explains the projection of x on Y.
langue originale | Anglais |
---|---|
titre | ESANN 2020 |
Sous-titre | 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning |
Lieu de publication | Bruges, Belgium |
Editeur | ESANN (i6doc.com) |
Pages | 393-398 |
ISBN (Electronique) | 978-287587074-2 |
ISBN (imprimé) | 9978-2-87587-073-5 |
Etat de la publication | Publié - 21 oct. 2020 |
Evénement | 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN2020 - Bruges, Belgique Durée: 2 oct. 2020 → 4 oct. 2020 |
Une conférence
Une conférence | 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning |
---|---|
Pays/Territoire | Belgique |
La ville | Bruges |
période | 2/10/20 → 4/10/20 |
Empreinte digitale
Examiner les sujets de recherche de « Explaining t-SNE embeddings locally by adapting LIME ». Ensemble, ils forment une empreinte digitale unique.Thèses de l'étudiant
-
Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction
Auteur: Bibal, A., 16 nov. 2020Superviseur: FRENAY, B. (Promoteur), VANHOOF, W. (Président), Cleve, A. (Jury), Dumas, B. (Jury), Lee, J. A. (Personne externe) (Jury) & Galarraga, L. A. (Personne externe) (Jury)
Student thesis: Doc types › Docteur en Sciences
Fichier