Summary of Towards Trustable Shap Scores, by Olivier Letoffe et al.
Towards trustable SHAP scores
by Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva
First submitted to arxiv on: 30 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 abstract discusses a new approach to Shapley values in explainable artificial intelligence (XAI) that addresses the limitations of previous methods. The proposed modification aims to extend axiomatic aggregations to Shapley values, which can lead to unsatisfactory results for certain ML models. This is achieved by introducing a novel definition of SHAP scores that avoids known limitations and has negligible impact on performance. The paper also characterizes the complexity of computing these new SHAP scores and provides modifications to existing implementations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The abstract proposes a new approach to Shapley values in XAI, which can help address the limitations of previous methods. This new approach aims to extend axiomatic aggregations to Shapley values, making it possible to get accurate results for certain ML models. The paper also discusses how to compute these new SHAP scores and provides modifications to existing implementations. |
