# Accounting for Unobserved Confounding in Domain Generalization

arXiv: https://arxiv.org/abs/2007.10653 · HTML: https://mlsanity.com/paper/2007.10653/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2020.

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

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [Regularizing towards Causal Invariance: Linear Models with Proxies](https://mlsanity.com/paper/2103.02477/) (2021)
- [Causal Balancing for Domain Generalization](https://mlsanity.com/paper/2206.05263/) (2022)
- [Variational Disentanglement for Domain Generalization](https://mlsanity.com/paper/2109.05826/) (2021)
- [Are Bias Mitigation Techniques for Deep Learning Effective?](https://mlsanity.com/paper/2104.00170/) (2021)
- [Domain Generalization -- A Causal Perspective](https://mlsanity.com/paper/2209.15177/) (2022)
- [Deconfounded Score Method: Scoring DAGs with Dense Unobserved Confounding](https://mlsanity.com/paper/2103.15106/) (2021)
- [Why Do Probabilistic Clinical Models Fail To Transport Between Sites?](https://mlsanity.com/paper/2311.04787/) (2023)
- [Learning Optimal Features via Partial Invariance](https://mlsanity.com/paper/2301.12067/) (2023)
- [Bias Challenges in Counterfactual Data Augmentation](https://mlsanity.com/paper/2209.05104/) (2022)
- [Direct-Effect Risk Minimization for Domain Generalization](https://mlsanity.com/paper/2211.14594/) (2022)
- [Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty](https://mlsanity.com/paper/2503.06158/) (2025)

## Abstract (arXiv)

This paper investigates the problem of learning robust, generalizable prediction models from a combination of multiple datasets and qualitative assumptions about the underlying data-generating model. Part of the challenge of learning robust models lies in the influence of unobserved confounders that void many of the invariances and principles of minimum error presently used for this problem. Our approach is to define a different invariance property of causal solutions in the presence of unobserved confounders which, through a relaxation of this invariance, can be connected with an explicit distributionally robust optimization problem over a set of affine combination of data distributions. Concretely, our objective takes the form of a standard loss, plus a regularization term that encourages partial equality of error derivatives with respect to model parameters. We demonstrate the empirical performance of our approach on healthcare data from different modalities, including image, speech and tabular data.