Abstract
Machine learning (ML) applications have automated numerous real-life tasks,
improving both private and public life. However, the black-box nature of many
state-of-the-art models poses the challenge of model verification; how can one
be sure that the algorithm bases its decisions on the proper criteria, or that it
does not discriminate against certain minority groups? In this paper we propose
a way to generate diverse counterfactual explanations from multilinear models,
a broad class which includes Random Forests, as well as Bayesian Networks.
improving both private and public life. However, the black-box nature of many
state-of-the-art models poses the challenge of model verification; how can one
be sure that the algorithm bases its decisions on the proper criteria, or that it
does not discriminate against certain minority groups? In this paper we propose
a way to generate diverse counterfactual explanations from multilinear models,
a broad class which includes Random Forests, as well as Bayesian Networks.
| Original language | English |
|---|---|
| Pages (from-to) | 1421-1443 |
| Number of pages | 23 |
| Journal | Machine Learning |
| Volume | 113 |
| Issue number | 3 |
| Early online date | 10 Jan 2024 |
| DOIs | |
| Publication status | Published - 1 Mar 2024 |
Keywords / Materials (for Non-textual outputs)
- XAI
- counterfactuals
- multilinear models