# Learning Functional Causal Models with Generative Neural Networks

arXiv: https://arxiv.org/abs/1709.05321 · HTML: https://mlsanity.com/paper/1709.05321/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2017.

## Built on by (most cited first, 14 of 14)

- [Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning](https://mlsanity.com/paper/2202.08816/) (2022)
- [Best of both worlds: local and global explanations with human-understandable concepts](https://mlsanity.com/paper/2106.08641/) (2021)
- [Benchmarking Counterfactual Image Generation](https://mlsanity.com/paper/2403.20287/) (2024)
- [Estimating Categorical Counterfactuals via Deep Twin Networks](https://mlsanity.com/paper/2109.01904/) (2021)
- [Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation](https://mlsanity.com/paper/2501.11309/) (2025)
- [Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-making](https://mlsanity.com/paper/2204.05030/) (2022)
- [SketchXAI: A First Look at Explainability for Human Sketches](https://mlsanity.com/paper/2304.11744/) (2023)
- [Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine](https://mlsanity.com/paper/2110.07785/) (2021)
- [Follow Us and Become Famous! Insights and Guidelines From Instagram Engagement Mechanisms](https://mlsanity.com/paper/2301.06815/) (2023)
- [Explainability in AI Based Applications: A Framework for Comparing Different Techniques](https://mlsanity.com/paper/2410.20873/) (2024)
- [A Unified Concept-Based System for Local, Global, and Misclassification Explanations](https://mlsanity.com/paper/2306.03531/) (2023)
- [A Moonshot for AI Oracles in the Sciences](https://mlsanity.com/paper/2406.17836/) (2024)
- [Towards Explainable Automated Data Quality Enhancement without Domain Knowledge](https://mlsanity.com/paper/2409.10139/) (2024)
- [Interpretability Framework for LLMs in Undergraduate Calculus](https://mlsanity.com/paper/2510.17910/) (2025)

## Abstract (arXiv)

We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN). CGNN leverages the power of neural networks to learn a generative model of the joint distribution of the observed variables, by minimizing the Maximum Mean Discrepancy between generated and observed data. An approximate learning criterion is proposed to scale the computational cost of the approach to linear complexity in the number of observations. The performance of CGNN is studied throughout three experiments. Firstly, CGNN is applied to cause-effect inference, where the task is to identify the best causal hypothesis out of Xrightarrow Y and Yrightarrow X. Secondly, CGNN is applied to the problem of identifying v-structures and conditional independences. Thirdly, CGNN is applied to multivariate functional causal modeling: given a skeleton describing the direct dependences in a set of random variables X = [X1, ldots, Xd], CGNN orients the edges in the skeleton to uncover the directed acyclic causal graph describing the causal structure of the random variables. On all three tasks, CGNN is extensively assessed on both artificial and real-world data, comparing favorably to the state-of-the-art. Finally, CGNN is extended to handle the case of confounders, where latent variables are involved in the overall causal model.