Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations
Loading...
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models develops significantly, offering numerous techniques to extract explanations from models. However, evaluating explanations is often not trivial, and differences in applied metrics can be subtle, especially with non-intelligible data. Thus, there is a need for visualizations tailored to explore explanations for domains with such data, e.g., time series. We propose DAVOTS, an interactive visual analytics approach to explore raw time series data, activations of neural networks, and attributions in a dense-pixel visualization to gain insights into the data, models' decisions, and explanations. To further support users in exploring large datasets, we apply clustering approaches to the visualized data domains to highlight groups and present ordering strategies for individual and combined data exploration to facilitate finding patterns. We visualize a CNN trained on the FordA dataset to demonstrate the approach.
Description
CCS Concepts: Human-centered computing -> Visual analytics;Computing methodologies -> Neural networks
@inproceedings{10.2312:mlvis.20231113,
booktitle = {Machine Learning Methods in Visualisation for Big Data},
editor = {Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko},
title = {{Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations}},
author = {Schlegel, Udo and Keim, Daniel},
year = {2023},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-224-0},
DOI = {10.2312/mlvis.20231113}
}