"Would life be more interesting if I were in AI?" Answering Counterfactuals based on Probabilistic Inductive Logic Programming
This work addresses a specific limitation in probabilistic logic programming for causal inference, making it incremental by focusing on enabling counterfactual reasoning.
The authors tackled the problem of learning probabilistic logic programs from observational data that can support counterfactual queries, by proposing a language fragment that enables program reconstruction from induced distributions, resulting in programs capable of handling such queries.
Probabilistic logic programs are logic programs where some facts hold with a specified probability. Here, we investigate these programs with a causal framework that allows counterfactual queries. Learning the program structure from observational data is usually done through heuristic search relying on statistical tests. However, these statistical tests lack information about the causal mechanism generating the data, which makes it unfeasible to use the resulting programs for counterfactual reasoning. To address this, we propose a language fragment that allows reconstructing a program from its induced distribution. This further enables us to learn programs supporting counterfactual queries.