Causal scientific explanations from machine learning.

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 th...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 202; no. 6; pp. 1 - 17
Autor principal: Buijsman, Stefan
Formato: Artículo
Publicado: Springer Nature Dec2023
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=174170429&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 174170429
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Dec2023
      vid: 202
      iid: 6
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        174170429
        10.1007/s11229-023-04429-3
      ppf: 1
      ppct: 16
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 438KB
      tig:
        atl: Causal scientific explanations from machine learning.
      aug:
        au: Buijsman, Stefan
        affil: https://ror.org/02e2c7k09 TU Delft, Jaffalaan 5, 2628 BX, Delft, The Netherlands
      sug:
      keyword:
        Artificial intelligence
        Causal inference
        Machine learning
        Scientific explanation
      ab: 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.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Synthese is a copyright of Springer, 2023. All Rights Reserved.
      item: Synthese
      holder: Springer Nature
      dt:
        @attributes:
          year: 2023
    holdings:
      @attributes:
        islocal: N