Abstracting Causal Models

Beckers, Sander; Halpern, Joseph Y.

doi:10.1609/aaai.v33i01.33012678

Cited by 48 publications

(76 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We mentioned the example of a pandemic leading to a national disaster because the administration refrained from taking appropriate precautionary measures. Our intuition is that people can still make causal judgments in complex situations like these because they have the ability to construct mental models that abstract away many of the low-level details of the situation (see Beckers & Halpern, 2019;Ullman et al, 2017). So instead of mentally simulating what actions each person would have taken, one would need to abstract away from this low level, and then consider the counterfactual dependence between the variables of interest on a higher level of abstraction.…”

Section: Omissions Beyond the Physicalmentioning

confidence: 99%

A counterfactual simulation model of causation by omission

Stephan

2021

Cognition

View full text Add to dashboard Cite

When do people say that an event that didn't happen was a cause? We extend the counterfactual simulation model (CSM) of causal judgment (Gerstenberg, Goodman, Lagnado, & Tenenbaum, 2021) and test it in a series of three experiments that look at people's causal judgments about omissions in dynamic physical interactions. The problem of omissive causation highlights a series of questions that need to be answered in order to give an adequate causal explanation of why something happened: what are the relevant variables, what are their possible values, how are putative causal relationships evaluated, and how is the causal responsibility for an outcome attributed to multiple causes? The CSM predicts that people make causal judgments about omissions in physical interactions by using their intuitive understanding of physics to mentally simulate what would have happened in relevant counterfactual situations. Prior work has argued that normative expectations affect judgments of omissive causation. Here we suggest a concrete mechanism of how this happens: expectations affect what counterfactuals people consider, and the more certain people are that the counterfactual outcome would have been different from what actually happened, the more causal they judge the omission to be. Our experiments show that both the structure of the physical situation as well as expectations about what will happen affect people's judgments.

show abstract

Section: Omissions Beyond the Physicalmentioning

confidence: 99%

A counterfactual simulation model of causation by omission

Stephan

2021

Cognition

View full text Add to dashboard Cite

show abstract

“…parts of the causal graph or some of the structural equation, might suffice in many contexts to prove that a change in classification is unjustified. Moreover, for conceptually lessstructured feature spaces, higher-order causal models (Beckers and Halpern 2019) where features such as objects are supervened by lower-order features such as pixels may provide the right level of description to define misclassification.…”

Section: Limitations and Open Problemsmentioning

confidence: 99%

The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples

Freiesleben

2021

Minds & Machines

View full text Add to dashboard Cite

The same method that creates adversarial examples (AEs) to fool image-classifiers can be used to generate counterfactual explanations (CEs) that explain algorithmic decisions. This observation has led researchers to consider CEs as AEs by another name. We argue that the relationship to the true label and the tolerance with respect to proximity are two properties that formally distinguish CEs and AEs. Based on these arguments, we introduce CEs, AEs, and related concepts mathematically in a common framework. Furthermore, we show connections between current methods for generating CEs and AEs, and estimate that the fields will merge more and more as the number of common use-cases grows.

show abstract

“…If Hoel has provided only a formal approach to measuring the sense in which a higher level description of a system can be more informative, he will still have made a valuable contribution (cf. Beckers & Halpern, 2019 for another approach to this kind of question). By measuring the strength of an intervention in terms of effective information, he gives a helpful analysis of the formal circumstances under which a coarse-grained description of a system might be more (epistemically) beneficial than a fine-grained one, and consequently an analysis of the kinds of systems where an epistemically non-reductive 'special science' approach is most appropriate.…”

Section: Is It Really Emergent?mentioning

confidence: 99%

Causal emergence from effective information

Dewhurst

2021

Thought: A Journal of Philosophy

View full text Add to dashboard Cite

The past few years have seen several novel informationtheoretic measures of causal emergence developed within the scientific community. In this paper I will introduce one such measure, called 'effective information', and describe how it is used to argue for causal emergence. In brief, the idea is that certain kinds of complex system are structured such that an intervention characterised at the macro-level will be more informative than one characterised at the micro-level, and that this constitutes a form of causal emergence. Having introduced this proposal, I will then assess the extent to which it is genuinely 'causal' and/or 'emergent', and argue that it supports only an epistemic form of causal emergence that is not as exciting as it first seems.

show abstract

Abstracting Causal Models

Cited by 48 publications

References 5 publications

A counterfactual simulation model of causation by omission

A counterfactual simulation model of causation by omission

The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples

Causal emergence from effective information

Contact Info

Product

Resources

About