Machine Learning Methods in Visualisation for Big Data 2024

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3606999

Browse

Browsing Machine Learning Methods in Visualisation for Big Data 2024 by Title

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    DimVis: Interpreting Visual Clusters in Dimensionality Reduction With Explainable Boosting Machine
    (The Eurographics Association, 2024) SALMANIAN, PARISA; Chatzimparmpas, Angelos; Karaca, Ali Can; Martins, Rafael M.; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    Dimensionality Reduction (DR) techniques such as t-SNE and UMAP are popular for transforming complex datasets into simpler visual representations. However, while effective in uncovering general dataset patterns, these methods may introduce artifacts and suffer from interpretability issues. This paper presents DimVis, a visualization tool that employs supervised Explainable Boosting Machine (EBM) models (trained on user-selected data of interest) as an interpretation assistant for DR projections. Our tool facilitates high-dimensional data analysis by providing an interpretation of feature relevance in visual clusters through interactive exploration of UMAP projections. Specifically, DimVis uses a contrastive EBM model that is trained in real time to differentiate between the data inside and outside a cluster of interest. Taking advantage of the inherent explainable nature of the EBM, we then use this model to interpret the cluster itself via single and pairwise feature comparisons in a ranking based on the EBM model's feature importance. The applicability and effectiveness of DimVis are demonstrated via a use case and a usage scenario with real-world data. We also discuss the limitations and potential directions for future research.
  • Thumbnail Image
    Item
    Exploration of Preference Models using Visual Analytics
    (The Eurographics Association, 2024) Buchmüller, Raphael; Zymla, Mark-Matthias; Keim, Daniel; Butt, Miriam; Sevastjanova, Rita; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    The identification and integration of diverse viewpoints are key to sound decision-making. This paper introduces a novel Visual Analytics technique aimed at summarizing and comparing perspectives derived from established preference models. We use 2D projection and interactive visualization to explore user models based on subjective preference labels and extracted linguistic features. We then employ a pie-chart-like exploration design to enable the aggregation and simultaneous exploration of diverse preference groupings. The approach allows rotation and slicing interactions of the visual space. We demonstrate the technique's applicability and effectiveness through a use case in exploring the complex landscape of argument preferences. We highlight our designs potential to enhance decision-making processes within diverging preferences through Visual Analytics.
  • Thumbnail Image
    Item
    Introducing Fairness in Graph Visualization via Gradient Descent
    (The Eurographics Association, 2024) Hong, Seok-Hee; Liotta, Giuseppe; Montecchiani, Fabrizio; Nöllenburg, Martin; Piselli, Tommaso; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    Motivated by the need for decision-making systems that avoid bias and discrimination, the concept of fairness recently gained traction in the broad field of artificial intelligence, stimulating new research also within the information visualization community. In this paper, we introduce a notion of fairness in network visualization, specifically for straight-line drawings of graphs, a foundational paradigm in the field. We empirically investigate the following research questions: (i) What is the price of incorporating fairness constraints in straight-line drawings? (ii) How unfair is a straight-line drawing that does not optimize fairness as a primary objective? To tackle these questions, we implement an algorithm based on gradient-descent that can compute straight-line drawings of graphs by optimizing multi-objective functions. We experimentally show that one can significantly increase the fairness of a drawing by paying a relatively small amount in terms of reduced readability.
  • Thumbnail Image
    Item
    MLVis 2024: Frontmatter
    (The Eurographics Association, 2024) Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
  • Thumbnail Image
    Item
    User-Adaptive Visualizations: An Exploration with GPT-4
    (The Eurographics Association, 2024) Yanez, Fernando; Nobre, Carolina; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    Data visualizations aim to enhance cognition and data interpretation. However, individual differences impact visual analysis, suggesting a personalized approach may be more effective. Current efforts focus on the study of generating visualizations with Large Language Models, lacking the user personalization component. This project explores using such models, specifically GPT-4, for modifying data visualizations to tailor to individual user characteristics. We developed a study to test GPT-4's ability to generate personalized visualizations. Statistical analysis of our results shows that for some personas, GPT is effective at personalizing the visualization. However, not all personalizations led to statistically significant improvements, suggesting variability in the effectiveness of LLM-driven personalization. These findings underline the importance of further exploring how personalized visualizations can best meet diverse user needs.
  • Thumbnail Image
    Item
    Visualizing Riemannian data with Rie-SNE
    (The Eurographics Association, 2024) Bergsson, Andri; Hauberg, Søren; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    Faithful visualizations of data residing on manifolds must take the underlying geometry into account when producing a flat planar view of the data. In this paper, we extend the stochastic neighbor embedding (SNE) algorithm to data on general Riemannian manifolds. We replace standard Gaussian assumptions with Riemannian diffusion counterparts and propose an efficient approximation that only requires access to calculations of Riemannian distances and volumes. We demonstrate that the approach also allows for mapping data from one manifold to another, e.g. from a high-dimensional sphere to a low-dimensional one.