Explaining t-SNE Embeddings Locally by Adapting LIME

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

1 Downloads (Pure)

Abstract

Non-linear dimensionality reduction techniques, such ast-SNE, are widely used to visualize and analyze high-dimensional datasets.While non-linear projections can be of high quality, it is hard, or evenimpossible, to interpret the dimensions of the obtained embeddings. Thispaper adapts LIME to locally explaint-SNE embeddings. More precisely,the sampling and black-box-querying steps of LIME are modified so thatthey can be used to explaint-SNE locally. The result of the proposal is toprovide, for a particular instancexand a particulart-SNE embeddingY,an interpretable model that locally explains the projection ofxonY
Original languageEnglish
Title of host publicationProceedings of the ESANN 2020 conference
Publication statusAccepted/In press - 2020
Event28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN2020 - Bruges, Belgium
Duration: 2 Oct 20204 Oct 2020

Conference

Conference28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
CountryBelgium
CityBruges
Period2/10/204/10/20

Fingerprint Dive into the research topics of 'Explaining t-SNE Embeddings Locally by Adapting LIME'. Together they form a unique fingerprint.

Cite this