Review of Causal Discovery Methods Based on Graphical Models

By Clark Glymour, Kun Zhang, Peter Spirtes. Frontiers in Genetics, 2019

1,160 citations recorded by the source corpus.

A fundamental task in various disciplines of science, including biology, is to find underlying causal relations and make use of them. Causal relations can be seen if interventions are properly applied; however, in many cases they are difficult or even impossible to conduct. It is then necessary to discover causal relations by analyzing statistical properties of purely observational data, which is known as causal discovery or causal structure search. This paper aims to give a introduction to and a brief review of the computational methods for causal discovery that were developed in the past three decades, including constraint-based and score-based methods and those based on functional causal models, supplemented by some illustrations and applications.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/b068f111b4b7f436bb99b945e3191d8061fe531b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

D’ya Like DAGs? A Survey on Structure Learning and Causal Discovery (2021, background): “Similarly to the linear non-Gaussian case above, both models exploit structural asymmetries that are reflected in the (in)dependence of regression residuals [69, 100, 190, 277].”
Secure and Robust Machine Learning for Healthcare: A Survey (2020, background): “A comprehensive review of graphical causal models can be found in this recent study [191].”
Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models (2023, background): “Causal relationship discovery aims to reveal potential unknown causal relationships based purely on observed data [20].”
Causal Reasoning and Large Language Models: Opening a New Frontier for Causality (2023, background): “The ﬁrst is to restrict data-generating process to speciﬁc functional forms under which identiﬁcation of a single graph is possible (Glymour et al., 2019).”
Granger Causality: A Review and Recent Advances (2021, background): “The above requirements were discussed in Granger’s original and followup papers (Granger, 1969, 1980, 2001) and extensively by other authors (Stokes and Purdon, 2017; Maziarz, 2015); see also the recent review by Glymour et al. (2019).”
Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models (2023, background): “Causal relationship discovery aims to reveal potential unknown causal relationships based purely on observed data [19].”
Ethical Machine Learning in Healthcare (2020, background): “Modern ML and causal discovery techniques can identify sources of confounding at scale (100), although validation of such methods can be challenging because of the lack of counterfactual data.”
Masked Gradient-Based Causal Structure Learning (2019, methodology): “We refer the reader to Glymour et al. [8], Spirtes and Zhang [32] for more details and also a review of other methods.”
A survey of Bayesian Network structure learning (2021, positive): “We would highlight the paper by Glymour et al. (2019) which compares key algorithms discussed here (PC, FCI, and GES) to functional causal models where assumptions about the functional form of the effect, causes and noise relationships can be used to deduce causal relationships.”
Algorithmic Recourse: from Counterfactual Explanations to Interventions (2020, background): “Causal discovery of the true world model is out of scope, and we refer the interested reader to the works of Eberhardt (2017); Malinsky & Danks (2018), and Glymour et al. (2019).”