Towards Computing an Optimal Abstraction for Structural Causal Models

2022/08/01 by Fabio Massimo Zennaro, Paolo Turrini, Zennaro, Fabio Massimo +3 · 2 citations
Computer Science · Arts and Humanities · #Bayesian Modeling and Causal Inference #Machine Learning and Algorithms #Philosophy and History of Science

paper · doi:10.48550/arxiv.2208.00894

Abstract

Working with causal models at different levels of abstraction is an important feature of science. Existing work has already considered the problem of expressing formally the relation of abstraction between causal models. In this paper, we focus on the problem of learning abstractions. We start by defining the learning problem formally in terms of the optimization of a standard measure of consistency. We then point out the limitation of this approach, and we suggest extending the objective function with a term accounting for information loss. We suggest a concrete measure of information loss, and we illustrate its contribution to learning new abstractions.

Cited by

• Distributionally Robust Causal Abstractions
• Identifiability in Causal Abstractions: A Hierarchy of Criteria

Related

• Quantifying Consistency and Information Loss for Causal Abstraction Learning
• Learning Causal Abstractions of Linear Structural Causal Models
• Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions
• Causal Optimal Transport of Abstractions
• Causal Abstraction Inference under Lossy Representations