Problem
Research questions and friction points this paper is trying to address.
Model Visualization
Machine Learning Models
Model-Centric Analysis
Spatial and Temporal Behavior
Visualization Taxonomy
Visualization of Machine Learning Models through Their Spatial and Temporal Listeners
🤖 AI Summary
Existing research on model visualization predominantly emphasizes data or tasks, lacking a cohesive analytical framework centered on the model itself. This work proposes a model-centric, two-stage visualization approach: first capturing the spatial and temporal behaviors of models through abstract listeners, then integrating these insights into the classical information visualization pipeline. Drawing upon a corpus of 128 papers and 331 annotated visualizations, we systematically construct the first ontology-driven visualization framework oriented toward models. Our analysis reveals a prevailing emphasis on outcome presentation in current literature, while studies exploring model mechanisms—though comparatively scarce—demonstrate disproportionately high impact. This study establishes a new paradigm for the design of future model visualization techniques.
📝 Abstract
Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric two-stage framework that employs abstract listeners to capture spatial and temporal model behaviors, and then connects the translated model behavior data to the classical InfoVis pipeline. To apply the framework at scale, we build a retrieval-augmented human--large language model (LLM) extraction workflow and curate a corpus of 128 VIS/VAST ModelVis papers with 331 coded figures. Our analysis shows a dominant result-centric priority on visualizing model outcomes, quantitative/nominal data type, statistical charts, and performance evaluation. Citation-weighted trends further indicate that less frequent model-mechanism-oriented studies have disproportionately high impact while are less investigated recently. Overall, the framework is a general approach for comparing existing ModelVis systems and guiding possible future designs.
Innovation
Methods, ideas, or system contributions that make the work stand out.
model-centric visualization
spatial and temporal listeners
InfoVis pipeline
retrieval-augmented LLM
ModelVis taxonomy
🔎 Similar Papers
No similar papers found.
