Summary of Constructing Fair Latent Space For Intersection Of Fairness and Explainability, by Hyungjun Joo et al.
Constructing Fair Latent Space for Intersection of Fairness and Explainability
by Hyungjun Joo, Hyeonggeun Han, Sehwan Kim, Sangwoo Hong, Jungwoo Lee
First submitted to arxiv on: 23 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
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 novel module constructs a fair latent space by disentangling and redistributing labels and sensitive attributes, allowing faithful explanation while ensuring fairness in machine learning models. The module is attached to a pretrained generative model, transforming its biased latent space into a fair one without retraining the entire model. This approach demonstrates cost savings and improved explainability for biased decisions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to make sure that machine learning models are both fair and easy to understand. Right now, many studies have focused on making models fair, but they haven’t paid much attention to how we can also explain why the model made a certain decision. This is important because people need to be able to trust the decisions being made by these models. The new module created in this paper helps to solve this problem by creating a “fair latent space” that shows exactly why a decision was made. This approach has many benefits, including saving time and money. |
Keywords
» Artificial intelligence » Attention » Generative model » Latent space » Machine learning
