Summary of Cost-constrained Multi-label Group Feature Selection Using Shadow Features, by Tomasz Klonecki et al.
Cost-constrained multi-label group feature selection using shadow features
by Tomasz Klonecki, Paweł Teisseyre, Jaesung Lee
First submitted to arxiv on: 3 Aug 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG)
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 paper explores feature selection in multi-label classification with cost constraints, crucial in medicine where diagnostic test costs are high. The goal is to select features that predict label vectors without exceeding a budget. The proposed method involves two steps: sequentially selecting features until the budget is exhausted and then adding cost-free features using a stop rule based on shadow features. This approach avoids computationally demanding optimization of penalty parameters, as seen in existing methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this paper solves a big problem in medicine where doctors need to predict many diseases from blood tests, but these tests are expensive. The goal is to pick the most important features (like test results) that will help diagnose diseases without spending too much money. The new method does this by selecting features one by one until a budget is reached and then adding more free features. This approach is better than others because it doesn’t require complex calculations. |
Keywords
» Artificial intelligence » Classification » Feature selection » Optimization
