DeepAI AI Chat
Log In Sign Up

Abstracting Causal Models

by   Sander Beckers, et al.
cornell university

We consider a sequence of successively more restrictive definitions of abstraction for causal models, starting with a notion introduced by Rubenstein et al. (2017) called exact transformation that applies to probabilistic causal models, moving to a notion of uniform transformation that applies to deterministic causal models and does not allow differences to be hidden by the "right" choice of distribution, and then to abstraction, where the interventions of interest are determined by the map from low-level states to high-level states, and strong abstraction, which takes more seriously all potential interventions in a model, not just the allowed interventions. We show that procedures for combining micro-variables into macro-variables are instances of our notion of strong abstraction, as are all the examples considered by Rubenstein et al.


page 1

page 2

page 3

page 4


Causal Abstraction for Faithful Model Interpretation

A faithful and interpretable explanation of an AI model's behavior and i...

Approximate Causal Abstraction

Scientific models describe natural phenomena at different levels of abst...

Causal Consistency of Structural Equation Models

Complex systems can be modelled at various levels of detail. Ideally, ca...

Active Invariant Causal Prediction: Experiment Selection through Stability

A fundamental difficulty of causal learning is that causal models can ge...

Causal Abstraction with Soft Interventions

Causal abstraction provides a theory describing how several causal model...

Meaningful Causal Aggregation and Paradoxical Confounding

In aggregated variables the impact of interventions is typically ill-def...

A Quantitative Account of Harm

In a companion paper (Beckers et al. 2022), we defined a qualitative not...