Show Me Similar Nodes: The Similarity Lens for Multivariate Graphs
Loading...
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Node-link diagrams with topology-driven layouts are effective tools for visually exploring the structure of graphs. When exploring multivariate graphs, a frequent analytical question is to ask which graph nodes are similar in terms of their multivariate attribute values. Answering this question would usually involve switching to an attribute-driven layout or a different visual representation altogether. However, such context switches may ensue additional cognitive costs and hinder the fluent exploration of the graph. In this paper, we present an interactive lens technique, called the similarity lens. It avoids global view changes by dynamically injecting a local attribute-driven layout into an otherwise topology-driven layout. Given a focus node of interest in the center of the lens, dissimilar nodes are pushed out of the lens and similar nodes are pulled inward, with the most similar nodes closest to the focus node. This dynamic layout adaptation facilitates comparison tasks on a local level without disturbing the user's overall mental map of the graph topology too much. We demonstrate the utility of our approach by exploring a real-world multivariate graph of soccer players.
Description
CCS Concepts: Human-centered computing → Visualization techniques; Interaction techniques
@inproceedings{10.2312:evs.20241059,
booktitle = {EuroVis 2024 - Short Papers},
editor = {Tominski, Christian and Waldner, Manuela and Wang, Bei},
title = {{Show Me Similar Nodes: The Similarity Lens for Multivariate Graphs}},
author = {Tominski, Christian and Berger, Philip},
year = {2024},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-251-6},
DOI = {10.2312/evs.20241059}
}