Summary of Interventional Fairness on Partially Known Causal Graphs: a Constrained Optimization Approach, by Aoqi Zuo et al.
Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
by Aoqi Zuo, Yiqing Li, Susan Wei, Mingming Gong
First submitted to arxiv on: 19 Jan 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 framework for achieving fair machine learning in scenarios where the true causal graph is partially known. Building upon recent advancements in causal inference, the approach leverages Partially Directed Acyclic Graphs (PDAGs) to model fair prediction and measure causal fairness. The PDAG is learned from observational data combined with domain knowledge, allowing for a balance between fairness and accuracy. Experimental results on both simulated and real-world datasets demonstrate the effectiveness of this method. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fair machine learning aims to prevent discrimination against individuals or sub-populations based on sensitive attributes like gender and race. Researchers have been using causal inference methods to measure unfairness by causal effects, but these methods often assume a known true causal graph, which isn’t realistic in many cases. This paper offers a new way to achieve fair machine learning when the true causal graph is only partially known. It uses something called a Partially Directed Acyclic Graph (PDAG) to model fair prediction and measure fairness. The PDAG is learned from data combined with expert knowledge. The results show that this approach works well on both fake and real-world datasets. |
Keywords
* Artificial intelligence * Inference * Machine learning
