Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks. One key property for robustness which the learned representation should capture and which recently received a lot of attention is described by the notion of invariance. In this work we provide a causal perspective and new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization, where we are able to significantly boost the score of existing models.
@article{arxiv.2206.11646,
title = {Invariant Causal Mechanisms through Distribution Matching},
author = {Mathieu Chevalley and Charlotte Bunne and Andreas Krause and Stefan Bauer},
journal= {arXiv preprint arXiv:2206.11646},
year = {2022}
}