Summary of Explanatory Model Monitoring to Understand the Effects Of Feature Shifts on Performance, by Thomas Decker et al.
Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance
by Thomas Decker, Alexander Koebler, Michael Lebacher, Ingo Thon, Volker Tresp, Florian Buettner
First submitted to arxiv on: 24 Aug 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 This paper proposes a novel approach called Explanatory Performance Estimation (XPE) to explain the behavior of black-box machine learning models under feature shifts. XPE combines concepts from Optimal Transport and Shapley Values to attribute an estimated performance change to interpretable input characteristics. The authors demonstrate the superiority of their method over several baselines on different datasets across various data modalities, including images, audio, and tabular data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand why machine learning models don’t work as well as they used to. It creates a new way to figure out what’s going wrong when a model’s performance drops. The method, called XPE, looks at the inputs that make the biggest difference in how well the model works. This can help us identify the problems and fix them before it’s too late. |
Keywords
» Artificial intelligence » Machine learning
