# Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks

arXiv: https://arxiv.org/abs/2410.06349 · HTML: https://mlsanity.com/paper/2410.06349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [What Are Bayesian Neural Network Posteriors Really Like?](https://mlsanity.com/paper/2104.14421/) (2021)
- [The Hardware Lottery](https://mlsanity.com/paper/2009.06489/) (2020)
- [Foundations of Structural Causal Models with Cycles and Latent Variables](https://mlsanity.com/paper/1611.06221/) (2016)
- [Generalizing to unseen domains via distribution matching](https://mlsanity.com/paper/1911.00804/) (2019)
- [Are Disentangled Representations Helpful for Abstract Visual Reasoning?](https://mlsanity.com/paper/1905.12506/) (2019)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Do Bayesian Neural Networks Need To Be Fully Stochastic?](https://mlsanity.com/paper/2211.06291/) (2022)
- [ACRE: Abstract Causal REasoning Beyond Covariation](https://mlsanity.com/paper/2103.14232/) (2021)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [Causal Transportability for Visual Recognition](https://mlsanity.com/paper/2204.12363/) (2022)
- [Bayesian Learning for Neural Networks: an algorithmic survey](https://mlsanity.com/paper/2211.11865/) (2022)
- [A General Algorithm for Deciding Transportability of Experimental Results](https://mlsanity.com/paper/1312.7485/) (2013)
- [Reparameterization invariance in approximate Bayesian inference](https://mlsanity.com/paper/2406.03334/) (2024)
- [A Survey of Methods, Challenges and Perspectives in Causality](https://mlsanity.com/paper/2302.00293/) (2023)

## Abstract (arXiv)

Deep neural networks can obtain impressive performance on various tasks under the assumption that their training domain is identical to their target domain. Performance can drop dramatically when this assumption does not hold. One explanation for this discrepancy is the presence of spurious domain-specific correlations in the training data that the network exploits. Causal mechanisms, in the other hand, can be made invariant under distribution changes as they allow disentangling the factors of distribution underlying the data generation. Yet, learning causal mechanisms to improve out-of-distribution generalisation remains an under-explored area. We propose a Bayesian neural architecture that disentangles the learning of the the data distribution from the inference process mechanisms. We show theoretically and experimentally that our model approximates reasoning under causal interventions. We demonstrate the performance of our method, outperforming point estimate-counterparts, on out-of-distribution image recognition tasks where the data distribution acts as strong adversarial confounders.