# Causal Generative Neural Networks

arXiv: https://arxiv.org/abs/1711.08936 · HTML: https://mlsanity.com/paper/1711.08936/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2017.

## Built on by (most cited first, 24 of 24)

- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Amortized Inference for Causal Structure Learning](https://mlsanity.com/paper/2205.12934/) (2022)
- [Size-Invariant Graph Representations for Graph Classification Extrapolations](https://mlsanity.com/paper/2103.05045/) (2021)
- [Efficient Neural Causal Discovery without Acyclicity Constraints](https://mlsanity.com/paper/2107.10483/) (2021)
- [Learning to Induce Causal Structure](https://mlsanity.com/paper/2204.04875/) (2022)
- [Causal Imitation Learning with Unobserved Confounders](https://mlsanity.com/paper/2208.06267/) (2022)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [Partial Identification of Treatment Effects with Implicit Generative Models](https://mlsanity.com/paper/2210.08139/) (2022)
- [Counterfactual Generative Models for Time-Varying Treatments](https://mlsanity.com/paper/2305.15742/) (2023)
- [Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting](https://mlsanity.com/paper/2302.08635/) (2023)
- [Neural Networks for Learning Counterfactual G-Invariances from Single Environments](https://mlsanity.com/paper/2104.10105/) (2021)
- [CauScale: Neural Causal Discovery at Scale](https://mlsanity.com/paper/2602.08629/) (2026)
- [Learning domain-specific causal discovery from time series](https://mlsanity.com/paper/2209.05598/) (2022)
- [Inferring the time-varying coupling of dynamical systems with temporal convolutional autoencoders](https://mlsanity.com/paper/2406.03212/) (2024)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [Topological Residual Asymmetry for Bivariate Causal Direction](https://mlsanity.com/paper/2602.00427/) (2026)
- [A Meta Learning Approach to Discerning Causal Graph Structure](https://mlsanity.com/paper/2106.05859/) (2021)
- [Causal Structural Hypothesis Testing and Data Generation Models](https://mlsanity.com/paper/2210.11275/) (2022)
- [A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations](https://mlsanity.com/paper/2311.00923/) (2023)
- [Large Causal Models for Temporal Causal Discovery](https://mlsanity.com/paper/2602.18662/) (2026)
- [Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution](https://mlsanity.com/paper/2605.02640/) (2026)
- [CausalRec: A CausalBoost Attention Model for Sequential Recommendation](https://mlsanity.com/paper/2510.21333/) (2025)
- [Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models](https://mlsanity.com/paper/2603.17384/) (2026)
- [Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection](https://mlsanity.com/paper/2606.03251/) (2026)

## Abstract (arXiv)

We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs leverage conditional independencies and distributional asymmetries to discover bivariate and multivariate causal structures. CGNNs make no assumption regarding the lack of confounders, and learn a differentiable generative model of the data by using backpropagation. Extensive experiments show their good performances comparatively to the state of the art in observational causal discovery on both simulated and real data, with respect to cause-effect inference, v-structure identification, and multivariate causal discovery.