Perplexity-free Parametric t-SNE

2020/10/03 by Francesco Crecchi, Crecchi, Francesco, Cyril de Bodt +7 · 1 citation
Computer Science · #Neural Networks and Applications #Face and Expression Recognition #Blind Source Separation Techniques

paper · pdf · doi:10.48550/arxiv.2010.01359

Abstract

The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm is a ubiquitously employed dimensionality reduction (DR) method. Its non-parametric nature and impressive efficacy motivated its parametric extension. It is however bounded to a user-defined perplexity parameter, restricting its DR quality compared to recently developed multi-scale perplexity-free approaches. This paper hence proposes a multi-scale parametric t-SNE scheme, relieved from the perplexity tuning and with a deep neural network implementing the mapping. It produces reliable embeddings with out-of-sample extensions, competitive with the best perplexity adjustments in terms of neighborhood preservation on multiple data sets.

Cited by

• AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings

Related

• Automatic Selection of t-SNE Perplexity
• Facilitate the Parametric Dimension Reduction by Gradient Clipping
• Conditional t-SNE: Complementary t-SNE embeddings through factoring out prior information
• Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings
• Kernel t-distributed stochastic neighbor embedding