Summary of Unifying Feature-based Explanations with Functional Anova and Cooperative Game Theory, by Fabian Fumagalli et al.
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
by Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier, Barbara Hammer, Julia Herbinger
First submitted to arxiv on: 22 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 unified framework for local and global feature-based explanations leverages functional ANOVA from statistics and game-theoretic measures to determine the influence of feature distributions and higher-order interactions. The framework combines these two dimensions to compare a wide range of explanation techniques for features and groups of features. This work introduces three fANOVA decompositions and showcases its effectiveness on synthetic and real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper creates a new way to understand how machine learning models make decisions. It looks at different methods, like perturbations or gradients, that try to explain these decisions. The problem is that we don’t know much about what makes these methods different, which limits their use in real-world situations. This paper fixes this by introducing a single framework that combines two existing ideas from statistics and game theory. It then shows how this framework can be used to compare and understand many different explanation techniques. |
Keywords
» Artificial intelligence » Machine learning
