Summary of Refining Counterfactual Explanations with Joint-distribution-informed Shapley Towards Actionable Minimality, by Lei You et al.
Refining Counterfactual Explanations With Joint-Distribution-Informed Shapley Towards Actionable Minimality
by Lei You, Yijun Bian, Lele Cao
First submitted to arxiv on: 7 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Methodology (stat.ME)
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 proposed method for generating counterfactual explanations (CE) in machine learning (ML) aims to optimize the required feature changes while maintaining the validity of CE without restricting models or CE algorithms. By computing a joint distribution between observed and counterfactual data using optimal transport (OT), the method derives Shapley values for feature attributions (FA). This approach is demonstrated on multiple datasets, showcasing its effectiveness in refining CE towards greater actionable efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Counterfactual explanations help us understand how machine learning models make decisions. Currently, methods that create these explanations often include too much information, making them hard to use. To fix this, a new method has been developed that minimizes the extra details while still giving accurate explanations. This is achieved by combining observed and counterfactual data using a special formula called optimal transport (OT). The new method was tested on many different datasets and showed it can make CE more useful. |
Keywords
* Artificial intelligence * Machine learning
