# Estimating Causal Effects from Learned Causal Networks

arXiv: https://arxiv.org/abs/2408.14101 · HTML: https://mlsanity.com/paper/2408.14101/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 37 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 7 of 7)

- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Partial Counterfactual Identification from Observational and Experimental Data](https://mlsanity.com/paper/2110.05690/) (2021)
- [Neural Causal Models for Counterfactual Identification and Estimation](https://mlsanity.com/paper/2210.00035/) (2022)
- [The Bayesian Structural EM Algorithm](https://mlsanity.com/paper/1301.7373/) (2013)
- [Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variables](https://mlsanity.com/paper/2003.12659/) (2020)
- [Causal Inference Using Tractable Circuits](https://mlsanity.com/paper/2202.02891/) (2022)
- [Join-Graph Propagation Algorithms](https://mlsanity.com/paper/1401.3489/) (2014)

## Built on by (most cited first, 3 of 3)

- [Your Assumed DAG is Wrong and Here's How To Deal With It](https://mlsanity.com/paper/2502.17030/) (2025)
- [Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments](https://mlsanity.com/paper/2504.11901/) (2025)
- [Graph-based Complexity for Causal Effect by Empirical Plug-in](https://mlsanity.com/paper/2411.10008/) (2024)

## Abstract (arXiv)

The standard approach to answering an identifiable causal-effect query (e.g., P(Y|do(X)) when given a causal diagram and observational data is to first generate an estimand, or probabilistic expression over the observable variables, which is then evaluated using the observational data. In this paper, we propose an alternative paradigm for answering causal-effect queries over discrete observable variables. We propose to instead learn the causal Bayesian network and its confounding latent variables directly from the observational data. Then, efficient probabilistic graphical model (PGM) algorithms can be applied to the learned model to answer queries. Perhaps surprisingly, we show that this model completion learning approach can be more effective than estimand approaches, particularly for larger models in which the estimand expressions become computationally difficult. We illustrate our method's potential using a benchmark collection of Bayesian networks and synthetically generated causal models.