Hierarchy Representation of Data in Machine Learnings
This work addresses the need for better interpretability in machine learning models by providing a visualization tool for understanding target hierarchies, but it appears incremental as it builds on existing concepts of model judgment patterns.
The paper tackles the problem of visualizing hierarchical relationships among data points based on model judgment patterns, proposing a method to represent when models consistently judge targets correctly or incorrectly together, which is intended to aid in model improvement.
When there are models with clear-cut judgment results for several data points, it is possible that most models exhibit a relationship where if they correctly judge one target, they also correctly judge another target. Conversely, if most models incorrectly judge one target, they may also incorrectly judge another target. We propose a method for visualizing this hierarchy among targets. This information is expected to be beneficial for model improvement.