Interactive dense pixel visualizations for time series and model attribution explanations
This work addresses the need for better visualization tools to explore explanations in domains like time series, but it is incremental as it builds on existing XAI techniques with a focus on visual analytics.
The authors tackled the challenge of evaluating explanations in Explainable AI for deep neural networks, especially with non-intelligible data like time series, by proposing DAVOTS, an interactive visual analytics approach that integrates raw data, model activations, and attributions in dense-pixel visualizations, demonstrated on a CNN trained on the FordA dataset.
The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models has developed 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.