InstanceFlow: Visualizing the Evolution of Classifier Confusion at the Instance Level

摘要

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 improve classification performance. The increasing complexity of models has led to a growing demand to make them interpretable through visualization. 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 at 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. Thus, 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.