Summary of Exploring the Relationship Between Feature Attribution Methods and Model Performance, by Priscylla Silva et al.
Exploring the Relationship Between Feature Attribution Methods and Model Performance
by Priscylla Silva, Claudio T. Silva, Luis Gustavo Nonato
First submitted to arxiv on: 22 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning models are crucial in educational settings, especially for predicting student success. The paper aims to bridge the gap in understanding factors influencing these predictions by exploring explainability within education. It employs nine different explanation methods and conducts a comprehensive analysis to examine the correlation between agreement among these methods and predictive model performance. The findings reveal a very strong correlation between the model’s performance and the level of agreement observed among the explanation methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research study is about machine learning models used in schools to predict student success. The goal is to figure out what makes these predictions good or bad. To do this, the scientists used nine different ways to explain why a model predicted something. They found that when many of these explanations agree with each other, the model’s prediction is usually right. |
Keywords
» Artificial intelligence » Machine learning
