Insight-SNE: Understanding t-SNE Embeddings through Interactive Explanation

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

17 Downloads (Pure)

Abstract

Non-linear dimensionality reduction techniques offer insights into complex datasets, yet interpreting them poses challenges. While some papers provide methods for explaining DR, and others focus on interactively exploring embeddings, there are currently no works that seamlessly combine both aspects. Our contributions, Insight-SNE, propose an interactive tool that allows exploring t-SNE embeddings and their related gradient-based explanations, as well as its evaluation with expert users.
Original languageEnglish
Title of host publicationEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Subtitle of host publicationESANN
PublisherESANN (i6doc.com)
Publication statusPublished - 2024

Fingerprint

Dive into the research topics of 'Insight-SNE: Understanding t-SNE Embeddings through Interactive Explanation'. Together they form a unique fingerprint.

Cite this