Journal
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
Volume 27, Issue 1, Pages 241-253Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2020.3011155
Keywords
Dimensionality reduction; Data visualization; Visualization; Analytical models; Manifolds; Data models; Support vector machines; Visual analysis; dimension reduction; class separation
Categories
Funding
- U.S. Department of Homeland Security [2017-ST-061-QA0001, 17STQAC00001-03-03]
- National Science Foundation [1939725]
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [1939725] Funding Source: National Science Foundation
Ask authors/readers for more resources
The article discusses the analysis of high-dimensional labeled data and proposes a visual analysis approach that utilizes the power of explainability from linear projections to explore non-linear separation structures by extracting locally linear segments approximating the original non-linear separations. Unlike traditional projection-based analysis, this approach supports the exploration of complex class separations through multiple local projection results.
High-dimensional labeled data widely exists in many real-world applications such as classification and clustering. One main task in analyzing such datasets is to explore class separations and class boundaries derived from machine learning models. Dimension reduction techniques are commonly applied to support analysts in exploring the underlying decision boundary structures by depicting a low-dimensional representation of the data distributions from multiple classes. However, such projection-based analyses are limited due to their lack of ability to show separations in complex non-linear decision boundary structures and can suffer from heavy distortion and low interpretability. To overcome these issues of separability and interpretability, we propose a visual analysis approach that utilizes the power of explainability from linear projections to support analysts when exploring non-linear separation structures. Our approach is to extract a set of locally linear segments that approximate the original non-linear separations. Unlike traditional projection-based analysis where the data instances are mapped to a single scatterplot, our approach supports the exploration of complex class separations through multiple local projection results. We conduct case studies on two labeled datasets to demonstrate the effectiveness of our approach.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available