Typing assumptions improve identification in causal discovery

by   Philippe Brouillard, et al.

Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. Under assumptions about the data-generative process, the causal graph can often be identified up to an equivalence class. Proposing new realistic assumptions to circumscribe such equivalence classes is an active field of research. In this work, we propose a new set of assumptions that constrain possible causal relationships based on the nature of the variables. We thus introduce typed directed acyclic graphs, in which variable types are used to determine the validity of causal relationships. We demonstrate, both theoretically and empirically, that the proposed assumptions can result in significant gains in the identification of the causal graph.


page 1

page 2

page 3

page 4


Identifiability of Causal Graphs using Functional Models

This work addresses the following question: Under what assumptions on th...

Causal Structure Learning: a Combinatorial Perspective

In this review, we discuss approaches for learning causal structure from...

Local Causal Discovery for Estimating Causal Effects

Even when the causal graph underlying our data is unknown, we can use ob...

Causal Discovery with Language Models as Imperfect Experts

Understanding the causal relationships that underlie a system is a funda...

TSLiNGAM: DirectLiNGAM under heavy tails

One of the established approaches to causal discovery consists of combin...

DAG With Omitted Objects Displayed (DAGWOOD): A framework for revealing causal assumptions in DAGs

Directed acyclic graphs (DAGs) are frequently used in epidemiology as a ...

Foundations of Causal Discovery on Groups of Variables

Discovering causal relationships from observational data is a challengin...

Please sign up or login with your details

Forgot password? Click here to reset