Summary of Lens Functions For Exploring Umap Projections with Domain Knowledge, by Daniel M. Bot et al.
Lens functions for exploring UMAP Projections with Domain Knowledge
by Daniel M. Bot, Jan Aerts
First submitted to arxiv on: 15 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computational Geometry (cs.CG); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed research adapts dimensionality reduction algorithms to enable domain knowledge guided interactive exploration of high-dimensional data. Building upon existing techniques, the study presents three types of lens functions for UMAP, a state-of-the-art algorithm, allowing analysts to adapt projections to their questions and reveal hidden patterns. The effectiveness of these lens functions is demonstrated in two use cases, while their computational cost is analyzed through a synthetic benchmark. This implementation is available as an open-source Python package. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Dimensionality reduction algorithms help us visualize big datasets. Typically, we use prior information to highlight or hide expected patterns in the projections. In this study, researchers developed three types of “lens” functions for a popular dimensionality reduction algorithm called UMAP. These lens functions allow experts to adapt the projections to fit their specific questions and reveal hidden patterns that might be missed otherwise. The researchers tested these lens functions with real-world data and analyzed how long they took to compute. You can even use this new technique yourself by installing an open-source Python package! |
Keywords
» Artificial intelligence » Dimensionality reduction » Umap
