= Menu

embComp: Visual Interactive Comparison of Vector Embeddings

Florian Heimerl, Kralj Christoph, Torsten Moller, Michael Gleicher
IEEE Transactions on Visualization and Computer Graphics, Volume TBD — 2021
Download the publication : accepted_version.pdf [7.9Mo]  
This paper introduces \sysname, a novel approach for comparing two embeddings that capture the similarity between objects, such as word and document embeddings. We survey scenarios where comparing these embedding spaces is useful. From those scenarios, we derive common tasks, introduce visual analysis methods that support these tasks, and combine them into a comprehensive system. One of \sysname's central features are overview visualizations that are based on metrics for measuring differences in the local structure around objects. Summarizing these local metrics over the embeddings provides global overviews of similarities and differences. Detail views allow comparison of the local structure around selected objects and relating this local information to the global views. Integrating and connecting all of these components, \sysname supports a range of analysis workflows that help understand similarities and differences between embedding spaces. We assess our approach by applying it in several use cases, including understanding corpora differences via word vector embeddings, and understanding algorithmic differences in generating embeddings.

Images and movies


BibTex references

  author       = "Heimerl, Florian and Christoph, Kralj and Moller, Torsten and Gleicher, Michael",
  title        = "embComp: Visual Interactive Comparison of Vector Embeddings",
  journal      = "IEEE Transactions on Visualization and Computer Graphics",
  volume       = "TBD",
  year         = "2021",
  note         = "accepted, pre-print ahead of publication",
  doi          = "10.1109/TVCG.2020.3045918",
  url          = "http://graphics.cs.wisc.edu/Papers/2021/HCMG21"

Other publications in the database