S+t-SNE - Bringing dimensionality reduction to data streams

We present S+t-SNE, an adaptation of the t-SNE algorithm designed to handle infinite data streams. The core idea behind S+t-SNE is to update the t-SNE embedding incrementally as new data arrives, ensuring scalability and adaptability to handle streaming scenarios. By selecting the most important points at each step, the algorithm ensures scalability while keeping informative visualisations. By employing a blind method for drift management, the algorithm adjusts the embedding space, which facilitates the visualisation of evolving data dynamics. Our experimental evaluations demonstrate the effectiveness and efficiency of S+t-SNE, whilst highlighting its ability to capture patterns in a streaming scenario. We hope our approach offers researchers and practitioners a real-time tool for understanding and interpreting high-dimensional data.

• Publication year

  2024

• Venue

  International Symposium on Intelligent Data Analysis

• Publication date

  2024-03-26

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1007/978-3-031-58553-1_8arXiv 2403.17643
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Concept Drift Detection in Data Stream Mining : A literature review

  2021cited by this paper
• openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding

  2019cited by this paper
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

  2018cited by this paper
• Visualizing Time-Dependent Data Using Dynamic t-SNE

  2016cited by this paper
• Piece wise Laplacian‐based Projection for Interactive Data Exploration and Organization

  2011cited by this paper
• Local Affine Multidimensional Projection

  2011cited by this paper
• STREAMIT: Dynamic visualization and interactive exploration of text streams

  2011cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Least Square Projection: A Fast High-Precision Multidimensional Projection Technique and Its Application to Document Mapping

  2008cited by this paper
• Truly Incremental Locally Linear Embedding

  2008cited by this paper
• Incremental nonlinear dimensionality reduction by manifold learning

  2006cited by this paper
• Incremental locally linear embedding

  2005cited by this paper
• Nonlinear Manifold Learning for Data Stream

  2004cited by this paper
• A spatio-temporal extension to Isomap nonlinear dimension reduction

  2004cited by this paper
• Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering

  2003cited by this paper
• Incremental multidimensional scaling method for database visualization

  1999cited by this paper
• DIMACS Series in Discrete Mathematics and Theoretical Computer Science Analysis of Approximate Nearest Neighbor Searching with Clustered Point Sets

  year unknowncited by this paper

• No citing papers are available for this paper.