Buijsman, Stefan (2023) Causal scientific explanations from Machine Learning. [Preprint]

Preview

Text Causal_scientific_explanations_from_Machine_Learning.pdf Download (394kB) | Preview

Abstract

Machine learning is used more and more in scientific contexts, from the recent breakthroughs with AlphaFold2 in protein fold prediction to the use of ML in parametrization for large climate/astronomy models. Yet it is unclear whether we can obtain scientific explanations from such models. I argue that when machine learning is used to conduct causal inference we can give a new positive answer to this question. However, these ML models are purpose-built models and there are technical results showing that standard machine learning models cannot be used for the same type of causal inference. Instead, there is a pathway to causal explanations from predictive ML models through new explainability techniques; specifically, new methods to extract structural equation models from such ML models. The extracted models are likely to suffer from issues though: they will often fail to account for confounders and colliders, as well as deliver simply incorrect causal graphs due to ML models tendency to violate physical laws such as the conservation of energy. In this case, extracted graphs are a starting point for new explanations, but predictive accuracy is no guarantee for good explanations.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Buijsman, Stefan s.n.r.buijsman@tudelft.nl 0000-0002-0004-0681
Keywords:	Explanations, Artificial Intelligence, Machine Learning, Causal explanations, Causal inference
Subjects:	General Issues > Causation Specific Sciences > Artificial Intelligence General Issues > Explanation
Depositing User:	Dr. Stefan Buijsman
Date Deposited:	15 Nov 2023 01:25
Last Modified:	15 Nov 2023 01:25
Item ID:	22772
Subjects:	General Issues > Causation Specific Sciences > Artificial Intelligence General Issues > Explanation
Date:	November 2023
URI:	https://philsci-archive.pitt.edu/id/eprint/22772

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item