Summary of Refresh: Responsible and Efficient Feature Reselection Guided by Shap Values, By Shubham Sharma et al.
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
by Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lecue, Daniele Magazzeni, Manuela Veloso
First submitted to arxiv on: 13 Mar 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 The paper proposes a novel method called REFRESH to efficiently reselect features in machine learning models, considering secondary performance characteristics such as fairness and robustness, without having to train new models from scratch. The authors introduce the problem of feature reselection, which is crucial for developing trustworthy artificial intelligence models that meet regulatory requirements. They propose an algorithm using SHAP values and correlation analysis to approximate predictions without training new models. Empirical evaluations on three datasets demonstrate REFRESH’s ability to find alternate models with better performance characteristics efficiently. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create more trustworthy AI models by allowing us to choose the right features for our machine learning models, even if we didn’t think about fairness and robustness at first. It does this by creating a new method called REFRESH that can pick good features without having to start from scratch every time. |
Keywords
* Artificial intelligence * Machine learning
