Causal Interpretability for Machine Learning – Problems, Methods and Evaluation


Raha Moraffah, Mansooreh Karami, Ruocheng Guo, Adrienne Raglin, Huan Liu

SIGKDD Explorations Newsletter 22(1), pages 18–33
June 2020

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy. To provide insights into the decision making processes of these models, a variety of traditional interpretable models have been proposed. Moreover, to generate more humanfriendly explanations, recent work on interpretability tries to answer questions related to causality such as "Why does this model makes such decisions?" or "Was it a specific feature that caused the decision made by the model?". In this work, models that aim to answer causal questions are referred to as causal interpretable models. The existing surveys have covered concepts and methodologies of traditional interpretability. In this work, we present a comprehensive survey on causal interpretable models from the aspects of the problems and methods. In addition, this survey provides in-depth insights into the existing evaluation metrics for measuring interpretability, which can help practitioners understand for what scenarios each evaluation metric is suitable.

(keywords) counterfactuals, interpratablity, causal inference, explainability, machine learning

Publications

Publications / Views

Home

Clouds
•  tags  •  authors  •  editors  •  journals  

Year
 2023    2022    2021    2020    2019    2018    2017    2016    2015    2014–1927

Sort
•  in journal  •  in proc  •  chapters  •  books  •  edited  •  spec issues  •  editorials  •  entries  •  manuals  •  tech reps  •  phd th  •  others  

Status
•  online  •  in press  •  proof  •  camera-ready  •  revised  •  accepted  •  revision  •  submitted  •  draft  •  note  

Services
•  ACM Digital Library  •  DBLP  •  IEEE Xplore  •  IRIS  •  PubMed  •  Google Scholar  •  Scopus  •  Semantic Scholar  •  Web of Science  •  DOI  

Publication

— authors

Raha Moraffah, Mansooreh Karami, Ruocheng Guo, Adrienne Raglin, Huan Liu

— status

published

— sort

article in journal

— publication date

June 2020

— journal

SIGKDD Explorations Newsletter

— volume

22

— issue

1

— pages

18–33

— number of pages

16

— address

New York, NY, USA

URLs

original page  |  open access PDF

identifiers

— DOI

10.1145/3400051.3400058

— print ISSN

1931-0145

files

Open Access PDF

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY