InstanceFlow: Visualizing the Evolution of Classifier Confusion on the Instance Level
This addresses the need for improved model interpretability in machine learning, particularly for researchers and practitioners dealing with complex classifiers, though it is incremental as it builds on existing visualization approaches.
The paper tackles the problem of analyzing classifier learning behavior over time by introducing InstanceFlow, a dual-view visualization tool that enables instance-level and temporal analysis, resulting in a system that bridges class-level and instance-level performance evaluation.
Classification is one of the most important supervised machine learning tasks. During the training of a classification model, the training instances are fed to the model multiple times (during multiple epochs) in order to iteratively increase the classification performance. The increasing complexity of models has led to a growing demand for model interpretability through visualizations. Existing approaches mostly focus on the visual analysis of the final model performance after training and are often limited to aggregate performance measures. In this paper we introduce InstanceFlow, a novel dual-view visualization tool that allows users to analyze the learning behavior of classifiers over time on the instance-level. A Sankey diagram visualizes the flow of instances throughout epochs, with on-demand detailed glyphs and traces for individual instances. A tabular view allows users to locate interesting instances by ranking and filtering. In this way, InstanceFlow bridges the gap between class-level and instance-level performance evaluation while enabling users to perform a full temporal analysis of the training process.