Browsing by Author "Scheibel, Willy"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Constructing Hierarchical Continuity in Hilbert & Moore Treemaps
    (The Eurographics Association, 2023) Scheibel, Willy; Döllner, Jürgen; Gillmann, Christina; Krone, Michael; Lenti, Simone
    The Hilbert and Moore treemap layout algorithms are based on the space-filling Hilbert and Moore curves, respectively, to map tree-structured datasets to a 2D treemap layout. Considering multiple snapshots of a time-variant dataset, one of the design goals for Hilbert and Moore treemaps is layout stability, i.e., low changes in the layout for low changes in the underlying tree-structured data. For this, their underlying space-filling curve is expected to be continuous across all nodes and hierarchy levels, which has to be considered throughout the layouting process. We propose optimizations to subdivision templates, their orientation, and discuss the continuity of the underlying space-filling curve. We show real-world examples of Hilbert and Moore treemaps for small and large datasets with continuous space-filling curves, allowing for improved layout stability.
  • Thumbnail Image
    Item
    A Dashboard for Interactive Convolutional Neural Network Training And Validation Through Saliency Maps
    (The Eurographics Association, 2023) Cech, Tim; Simsek, Furkan; Scheibel, Willy; Döllner, Jürgen; Gillmann, Christina; Krone, Michael; Lenti, Simone
    Quali-quantitative methods provide ways for interrogating Convolutional Neural Networks (CNN). For it, we propose a dashboard using a quali-quantitative method based on quantitative metrics and saliency maps. By those means, a user can discover patterns during the training of a CNN. With this, they can adapt the training hyperparameters of the model, obtaining a CNN that learned patterns desired by the user. Furthermore, they neglect CNNs which learned undesirable patterns. This improves users' agency over the model training process.
  • Thumbnail Image
    Item
    A Dashboard for Simplifying Machine Learning Models using Feature Importances and Spurious Correlation Analysis
    (The Eurographics Association, 2024) Cech, Tim; Kohlros, Erik; Scheibel, Willy; Döllner, Jürgen; Kucher, Kostiantyn; Diehl, Alexandra; Gillmann, Christina
    Machine Learning models underlie a trade-off between accurracy and explainability. Given a trained, complex model, we contribute a dashboard that supports the process to derive more explainable models, here: Fast-and-Frugal Trees, with further introspection using feature importances and spurious correlation analyses. The dashboard further allows to iterate over the feature selection and assess the trees' performance in comparison to the complex model.
  • Thumbnail Image
    Item
    Exploring High-Dimensional Data by Pointwise Filtering of Low-Dimensional Embeddings
    (The Eurographics Association, 2024) Atzberger, Daniel; Jobst, Adrian; Scheibel, Willy; Döllner, Jürgen; Hunter, David; Slingsby, Aidan
    Dimensionality reductions are a class of unsupervised learning algorithms that aim to find a lower-dimensional embedding for a high-dimensional dataset while preserving local and global structures. By representing a high-dimensional dataset as a twodimensional scatterplot, a user can explore structures within the dataset. However, dimensionality reductions inherit distortions that might result in false deductions. This work presents a visualization approach that combines a two-dimensional scatterplot derived from a dimensionality reduction with two pointwise filtering possibilities. Each point is associated with two pointwise metrics that quantify the correctness of its neighborhood and similarity to surrounding data points. By setting threshold for these two metrics, the user is supported in several scatterplot analytics tasks, e.g., class separation and outlier detection. We apply our visualization to a text corpus to detect interesting data points visually and discuss the findings.
  • Thumbnail Image
    Item
    Interactive Human-guided Dimensionality Reduction using Landmark Positioning
    (The Eurographics Association, 2024) Cech, Tim; Raue, Christian; Sadrieh, Frederic; Scheibel, Willy; Döllner, Jürgen; Kucher, Kostiantyn; Diehl, Alexandra; Gillmann, Christina
    Dimensionality Reduction Techniques (DRs) are used for projecting high-dimensional data onto a two-dimensional plane. One subclass of DRs are such techniques that utilize landmarks. Landmarks are a subset of the original data space that are projected by a slow and more precise technique. The other data points are then placed in relation to these landmarks with respect to their distance in the high-dimensional space. We propose a technique to refine the placement of the landmarks by a human user. We test two different techniques for unprojecting the movement of the low-dimensional landmarks into the high-dimensional data space. We showcase that such a movement can increase certain quality metrics while decreasing others. Therefore, users may use our technique to challenge their understanding of the high-dimensional data space.