Invariant Risk Minimization

5 Jul 2019  ·  Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz ·

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top of that data representation, matches for all training distributions. Through theory and experiments, we show how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.

PDF Abstract

Datasets

Introduced in the Paper:

Colored MNIST Colored-MNIST(with spurious correlation)
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification Colored-MNIST(with spurious correlation) MLP-IRM Accuracy 66.9 # 3
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy