t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections
t-viSNE: интерактивная оценка и интерпретация проекций t-SNE
2020-04-13
SCID: 54.1/2aaew2d2
Discuss with AI
dimensionality reductioninteractive visualizationneighborhood preservationt-SNE projectionsvisual analytics
Figures from the paper
Abstract (AI)
t-Distributed Stochastic Neighbor Embedding (t-SNE) for the visualization of multidimensional data has proven to be a popular approach, with successful applications in a wide range of domains. Despite their usefulness, t-SNE projections can be hard to interpret or even misleading, which hurts the trustworthiness of the results. Understanding the details of t-SNE itself and the reasons behind specific patterns in its output may be a daunting task, especially for non-experts in dimensionality reduction. In this article, we present t-viSNE, an interactive tool for the visual exploration of t-SNE projections that enables analysts to inspect different aspects of their accuracy and meaning, such as the effects of hyper-parameters, distance and neighborhood preservation, densities and costs of specific neighborhoods, and the correlations between dimensions and visual patterns. We propose a coherent, accessible, and well-integrated collection of different views for the visualization of t-SNE projections. The applicability and usability of t-viSNE are demonstrated through hypothetical usage scenarios with real data sets. Finally, we present the results of a user study where the tool's effectiveness was evaluated. By bringing to light information that would normally be lost after running t-SNE, we hope to support analysts in using t-SNE and making its results better understandable.
Key Findings
1
A user study evaluated t-viSNE’s effectiveness, supporting its use for exposing information normally lost after t-SNE computation and improving result understanding.
2
Hypothetical usage scenarios with real datasets demonstrate the tool’s applicability and usability.
3
The tool enables inspection of hyperparameter effects, distance and neighborhood preservation, local densities, neighborhood costs, and correlations between dimensions and visual patterns.
4
t-viSNE integrates multiple coordinated views into an accessible framework designed to help non-experts understand why specific t-SNE patterns emerge.
5
t-viSNE is an interactive tool for exploring t-SNE projections and assessing their accuracy, interpretability, and meaning.
Research Object
t-SNE projections of multidimensional data
Research Subject
Interactive assessment and interpretation of projection accuracy, meaning, and visualization patterns, including hyperparameter effects, distance and neighborhood preservation, local densities and costs, and correlations between dimensions and visual patterns
Publication Details
Publication Date
2020-04-13
Journal
Publisher
ISSN
Cited by
164
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest