WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings
This tool helps researchers and practitioners explore embeddings more easily, though it is incremental as it builds on existing visualization methods with new scalability features.
The paper tackles the challenge of interpreting and using large, high-dimensional machine learning embeddings by presenting WizMap, an interactive visualization tool that scales to millions of points directly in web browsers without backend servers.
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.