Abstraction between Structural Causal Models: A Review of Definitions and Properties

07/18/2022
by   Fabio Massimo Zennaro, et al.
0

Structural causal models (SCMs) are a widespread formalism to deal with causal systems. A recent direction of research has considered the problem of relating formally SCMs at different levels of abstraction, by defining maps between SCMs and imposing a requirement of interventional consistency. This paper offers a review of the solutions proposed so far, focusing on the formal properties of a map between SCMs, and highlighting the different layers (structural, distributional) at which these properties may be enforced. This allows us to distinguish families of abstractions that may or may not be permitted by choosing to guarantee certain properties instead of others. Such an understanding not only allows to distinguish among proposal for causal abstraction with more awareness, but it also allows to tailor the definition of abstraction with respect to the forms of abstraction relevant to specific applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/01/2022

Towards Computing an Optimal Abstraction for Structural Causal Models

Working with causal models at different levels of abstraction is an impo...
research
05/07/2023

Quantifying Consistency and Information Loss for Causal Abstraction Learning

Structural causal models provide a formalism to express causal relations...
research
01/14/2023

Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions

An abstraction can be used to relate two structural causal models repres...
research
05/07/2016

Matching models across abstraction levels with Gaussian Processes

Biological systems are often modelled at different levels of abstraction...
research
11/22/2022

Causal Abstraction with Soft Interventions

Causal abstraction provides a theory describing how several causal model...
research
09/11/2019

Abstraction for Zooming-In to Unsolvability Reasons of Grid-Cell Problems

Humans are capable of abstracting away irrelevant details when studying ...
research
05/07/2020

Expressing Accountability Patterns using Structural Causal Models

While the exact definition and implementation of accountability depend o...

Please sign up or login with your details

Forgot password? Click here to reset