Summary of Fgce: Feasible Group Counterfactual Explanations For Auditing Fairness, by Christos Fragkathoulas et al.
FGCE: Feasible Group Counterfactual Explanations for Auditing Fairness
by Christos Fragkathoulas, Vasiliki Papanikou, Evaggelia Pitoura, Evimaria Terzi
First submitted to arxiv on: 29 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Methodology (stat.ME)
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 presents a novel graph-based framework called Feasible Group Counterfactual Explanations (FGCEs) for auditing model fairness in machine learning. The framework generates group counterfactual explanations that reveal how inputs should change to achieve a desired outcome, which is crucial for understanding and mitigating unfairness. Unlike existing methods, FGCEs captures real-world feasibility constraints and constructs subgroups with similar counterfactuals. The paper also proposes measures tailored to group counterfactual generation to evaluate trade-offs between the number of counterfactuals, their associated costs, and the breadth of coverage achieved. Experimental results on benchmark datasets demonstrate the effectiveness of FGCEs in managing feasibility constraints and trade-offs, as well as the potential of proposed metrics in identifying and quantifying fairness issues. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to make sure machine learning models are fair and don’t unfairly treat certain groups. It introduces a new way to do this called Feasible Group Counterfactual Explanations (FGCEs). FGCEs shows how inputs should change to get a different outcome, which is important for making sure the model isn’t unfair. The paper also proposes new ways to measure fairness and makes it clear that its approach works well on real-world data. |
Keywords
» Artificial intelligence » Machine learning
