# Improving Model Robustness Using Causal Knowledge

arXiv: https://arxiv.org/abs/1911.12441 · HTML: https://mlsanity.com/paper/1911.12441/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation](https://mlsanity.com/paper/2103.00136/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge](https://mlsanity.com/paper/2102.06271/) (2021)
- [Navigating causal deep learning](https://mlsanity.com/paper/2212.00911/) (2022)
- [DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction](https://mlsanity.com/paper/2208.01373/) (2022)

## Abstract (arXiv)

For decades, researchers in fields, such as the natural and social sciences, have been verifying causal relationships and investigating hypotheses that are now well-established or understood as truth. These causal mechanisms are properties of the natural world, and thus are invariant conditions regardless of the collection domain or environment. We show in this paper how prior knowledge in the form of a causal graph can be utilized to guide model selection, i.e., to identify from a set of trained networks the models that are the most robust and invariant to unseen domains. Our method incorporates prior knowledge (which can be incomplete) as a Structural Causal Model (SCM) and calculates a score based on the likelihood of the SCM given the target predictions of a candidate model and the provided input variables. We show on both publicly available and synthetic datasets that our method is able to identify more robust models in terms of generalizability to unseen out-of-distribution test examples and domains where covariates have shifted.