Summary of The Susceptibility Of Example-based Explainability Methods to Class Outliers, by Ikhtiyor Nematov et al.
The Susceptibility of Example-Based Explainability Methods to Class Outliers
by Ikhtiyor Nematov, Dimitris Sacharidis, Tomer Sagi, Katja Hose
First submitted to arxiv on: 30 Jul 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 study examines how outliers in training data affect the performance of black-box machine learning models when using example-based explainability methods. The researchers reformulate existing evaluation metrics, such as correctness and relevance, to better suit these methods and introduce a new metric called distinguishability. They then highlight the limitations of current explainability approaches that aim to suppress class outliers by conducting experiments on two datasets (text classification and image classification) and evaluating four state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how noisy data affects AI models’ ability to explain their decisions. The researchers change how we measure how well these models do, making them better suited for these new “explainability” methods. They found that current approaches are not good enough because they don’t handle outliers well. This is important because it could help us create more reliable AI systems. |
Keywords
» Artificial intelligence » Image classification » Machine learning » Text classification
