Summary of Beyond Model Interpretability: Socio-structural Explanations in Machine Learning, by Andrew Smart and Atoosa Kasirzadeh
Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning
by Andrew Smart, Atoosa Kasirzadeh
First submitted to arxiv on: 5 Sep 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 explores the challenges of interpreting the outputs of opaque machine learning models. One approach is to develop interpretable techniques that provide local or global explanations. The authors argue that in certain domains, such as social philosophy, a third type of explanation – sociostructural explanation – is needed. This involves illustrating how social structures contribute to and explain the outputs of machine learning models. The paper proposes examining a racially biased healthcare algorithm to demonstrate the importance of sociostructural explanations. By understanding the outputs of machine learning systems, we can gain transparency beyond model interpretability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how we understand what machine learning models do. One way is by making them more understandable through interpretable techniques. The authors think that in some areas, like social issues, we need a new kind of explanation called sociostructural explanation. This helps us see how social structures affect the results of machine learning models. They use an example of a biased healthcare algorithm to show why this type of explanation is important. |
Keywords
» Artificial intelligence » Machine learning
