Explaining t-SNE embeddings locally by adapting LIME

Adrien Bibal; Viet Minh Vu; Geraldin Nanfack; Benoît Frénay

Explaining t-SNE embeddings locally by adapting LIME

Adrien Bibal, Viet Minh Vu, Geraldin Nanfack, Benoît Frénay

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

122 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	ESANN 2020
Subtitle of host publication	28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Place of Publication	Bruges, Belgium
Publisher	ESANN (i6doc.com)
Pages	393-398
ISBN (Electronic)	978-287587074-2
ISBN (Print)	9978-2-87587-073-5
Publication status	Published - 21 Oct 2020
Event	28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN2020 - Bruges, Belgium Duration: 2 Oct 2020 → 4 Oct 2020

Conference

Conference	28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Country/Territory	Belgium
City	Bruges
Period	2/10/20 → 4/10/20

Access to Document

2020-Bibal-Explaining t-SNE Embeddings Locally by Adapting LIMESubmitted manuscript, 932 KB
2020_BibalAEtal_Article_ExplainingAccepted author manuscript, 932 KB

https://dblp.org/db/conf/esann/esann2020.html

Cite this

@inproceedings{72df8a506a814971a75ced4054a0396f,

title = "Explaining t-SNE embeddings locally by adapting LIME",

abstract = "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.",

author = "Adrien Bibal and Vu, {Viet Minh} and Geraldin Nanfack and Beno{\^i}t Fr{\'e}nay",

note = "Funding Information: ∗The first three authors have contributed equally. G. Nanfack is funded by the EOS Ver-iLearn project n. 30992574 of the Fonds de la Recherche Scientifique (F.R.S-FNRS) in Belgium. Publisher Copyright: {\textcopyright} ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.; 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning : ESANN2020 ; Conference date: 02-10-2020 Through 04-10-2020",

year = "2020",

month = oct,

day = "21",

language = "English",

isbn = "9978-2-87587-073-5",

pages = "393--398",

booktitle = "ESANN 2020",

publisher = "ESANN (i6doc.com)",

}

Bibal, A , Vu, VM , Nanfack, G & Frénay, B 2020, Explaining t-SNE embeddings locally by adapting LIME. in ESANN 2020 : 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN (i6doc.com), Bruges, Belgium, pp. 393-398, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 2/10/20. <https://dblp.org/db/conf/esann/esann2020.html>

Explaining t-SNE embeddings locally by adapting LIME. / Bibal, Adrien ; Vu, Viet Minh ; Nanfack, Geraldin et al.
ESANN 2020 : 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges, Belgium: ESANN (i6doc.com), 2020. p. 393-398.

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Explaining t-SNE embeddings locally by adapting LIME

AU - Bibal, Adrien

AU - Vu, Viet Minh

AU - Nanfack, Geraldin

AU - Frénay, Benoît

N1 - Funding Information: ∗The first three authors have contributed equally. G. Nanfack is funded by the EOS Ver-iLearn project n. 30992574 of the Fonds de la Recherche Scientifique (F.R.S-FNRS) in Belgium. Publisher Copyright: © ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

PY - 2020/10/21

Y1 - 2020/10/21

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85098949059&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85098949059

SN - 9978-2-87587-073-5

SP - 393

EP - 398

BT - ESANN 2020

PB - ESANN (i6doc.com)

CY - Bruges, Belgium

T2 - 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Y2 - 2 October 2020 through 4 October 2020

ER -

Explaining t-SNE embeddings locally by adapting LIME

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction

Cite this

Explaining t-SNE embeddings locally by adapting LIME

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Student theses

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction

Cite this