Structural Compactness as a Complementary Criterion for Explanation Quality

1. 1Identify the need for a complementary criterion for explanation quality beyond simple statistics
2. 2Develop a graph-based structural metric, such as Minimum Spanning Tree Compactness (MST-C), to capture higher-order geometric properties
3. 3Apply MST-C to attributions to evaluate their legibility and quality
4. 4Analyze the results to improve model interpretability and trustworthiness

Data scientists and AI engineers on a team can benefit from this research as it provides a new criterion for evaluating explanation quality, which can improve model interpretability and trustworthiness

💡 MST-C captures higher-order geometric properties of attributions, such as spread and cohesion, to evaluate explanation quality

📊 New metric for explanation quality: Minimum Spanning Tree Compactness (MST-C) 📈