Summary of Froc: Building Fair Roc From a Trained Classifier, by Avyukta Manjunatha Vummintala et al.
FROC: Building Fair ROC from a Trained Classifier
by Avyukta Manjunatha Vummintala, Shantanu Das, Sujit Gujar
First submitted to arxiv on: 19 Dec 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 The paper explores fair probabilistic binary classification for protected groups by introducing a new fairness metric called ε1-Equalized ROC. It aims to transform an unfair classifier’s output into a randomized yet fair one that satisfies this metric. The authors propose a threshold query model and design a linear-time algorithm, FROC, to achieve this transformation while minimizing AUC loss. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making sure a machine learning model is fair when it has to make predictions for different groups of people. It wants to find a way to take an unfair model and turn its output into something that’s fair for everyone. The authors came up with a new way to measure fairness and developed an algorithm called FROC to achieve this. |
Keywords
* Artificial intelligence * Auc * Classification * Machine learning
