WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings

TL;DR

WizMap is an interactive, scalable visualization tool that enables users to explore and interpret large machine learning embeddings efficiently within web browsers, addressing challenges of high dimensionality and dataset size.

Contribution

The paper introduces WizMap, a novel multi-resolution embedding summarization method combined with a map-like interface for scalable, browser-based exploration of large embedding spaces.

Findings

Scales to millions of embeddings in web browsers

Enables intuitive navigation of high-dimensional spaces

Open-source tool accessible via a public demo

Abstract

Machine learning models often learn latent embedding representations that capture the domain semantics of their training data. These embedding representations are valuable for interpreting trained models, building new models, and analyzing new datasets. However, interpreting and using embeddings can be challenging due to their opaqueness, high dimensionality, and the large size of modern datasets. To tackle these challenges, we present WizMap, an interactive visualization tool to help researchers and practitioners easily explore large embeddings. With a novel multi-resolution embedding summarization method and a familiar map-like interaction design, WizMap enables users to navigate and interpret embedding spaces with ease. Leveraging modern web technologies such as WebGL and Web Workers, WizMap scales to millions of embedding points directly in users' web browsers and computational notebooks without the need for dedicated backend servers. WizMap is open-source and available at the following public demo link: https://poloclub.github.io/wizmap.