Stochastic Neighbor Embedding

By Geoffrey E. Hinton, Sam T. Roweis. 2002

2,334 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Statistical Learning Theory

Citations in the corpus

Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization (2020, background): “Hinton and Roweis (2003) introduced the Stochastic Neighborhood Embedding (SNE), which converts Euclidean distances between samples into conditional probabilities that represent similarities.”
The art of using t-SNE for single-cell transcriptomics (2018, methodology): “The t-SNE algorithm 9 is based on the SNE framework 47 .”
Information-theoretic Online Memory Selection for Continual Learning (2022, positive): “We also plot the memories using the TSNE visualization (Hinton & Roweis, 2002).”
Adding Gradient Noise Improves Learning for Very Deep Networks (2015, methodology): “An annealed Gaussian gradient noise schedule was used to train the highly non-convex Stochastic Neighbor Embedding model in Hinton & Roweis (2002).”
Learning To Retrieve Prompts for In-Context Learning (2021, methodology): “Figure 3 shows a t-SNE (Hinton and Roweis, 2002) projection of the embeddings learned by EPR for the training examples of BREAK, with a link to an interactive version, where we applied the OPTICS (Ankerst et al.”
Barnes-Hut-SNE (2013, methodology): “For creating two-or three-dimensional embeddings that can be readily visualized in a scatter plot, a family of techniques based on stochastic neighbor embedding (SNE; [11]) has recently become very popular.”
Semantic hashing (2009, methodology): “To see whether the learned 128-bit codes preserve class info rmation, we used stochastic neighbor embedding [9] to visualiz e the 128-bit codes of all the documents from 5 or 6 separate classe s.”
GPU accelerated t-distributed stochastic neighbor embedding (2019, methodology): “t-SNE is heavily based on Stochastic Neighbor Embedding (SNE) [18], which for any set of points in the lower-dimensional space, defines a similar probability:”
Inductive Hashing on Manifolds (2013, background): “t-SNE is a modification of stochastic neighborhood embedding (SNE) [13] which aims to overcome the tendency of that method to crowd points together in one location.”
Shift-invariant similarities circumvent distance concentration in stochastic neighbor embedding and variants (2011, methodology): “Recent and successful methods following this approach are stochastic neighbor embedding (SNE) [20] and its variants, t-distributed SNE (t-SNE) [21] and NeRV (standing for neighborhood retrieval and visualization) [22].”
Piecewise Flat Embedding for Image Segmentation (2018, background): “t-SNE [44], an extension of SNE [45], generates pleasant embedding results for the visualization of high dimensional data.”
Semi-supervised Kernel Metric Learning Using Relative Comparisons (2016, methodology): “Figure 3 shows a visualization of the USPS Digits dataset using the SNE method [Hinton and Roweis, 2003] in the original space, and the spaces induced by SK k m and SKLR .”
A more globally accurate dimensionality reduction method using triplets (2018, background): “Motivated by the fact that the humans essentially think in two or three dimensions, DR has been studied extensively throughout the years (Tenenbaum et al., 2000; Kohonen, 1998; Roweis & Saul, 2000; Hinton & Roweis, 2003; Maaten & Hinton, 2008).”
Latent Coincidence Analysis: A Hidden Variable Model for Distance Metric Learning (2012, methodology): “NCA was conceived as a supervised counterpart to stochastic neighborhood embedding [7], an unsupervised method for dimensionality reduction.”
Visualizing Data using t-SNE (2008, methodology): “In this respect, t-SNE differs from UNI-SNE, in which the strength of the repulsion between very dissimilar datapoints Algorithm 1 : Simple version of t-Distributed Stochastic Neighbor Embedding.”