Exploring the Relationship Between Feature Attribution Methods and Model Performance

2024/05/22 by Priscylla Silva, Silva, Priscylla, Claudio Silva +3 · 1 citation
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2405.13957

openalex publication_date 2024/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these models' predictions, especially in explainability within education. This work addresses this gap by employing nine distinct explanation methods and conducting a comprehensive analysis to explore the correlation between the agreement among these methods in generating explanations and the predictive model's performance. Applying Spearman's correlation, our findings reveal a very strong correlation between the model's performance and the agreement level observed among the explanation methods.

Cited by

• rCamInspector: Building Reliability and Trust on IoT (Spy) Camera Detection using XAI

Related

• Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs
• Evaluating Explanations: How much do explanations from the teacher aid students?
• Explaining Predictions from Machine Learning Models: Algorithms, Users, and Pedagogy
• Benchmarking Attribution Methods with Relative Feature Importance
• Unified Explanations in Machine Learning Models: A Perturbation Approach