Back to Search Start Over

Adversarial Invariant Learning

Authors :
Qianxiao Li
Xiao-Yun Zhou
Zhanxing Zhu
Nanyang Ye
Guang-Zhong Yang
Jingxuan Tang
Zhenguo Li
Huayu Deng
Source :
CVPR
Publication Year :
2021
Publisher :
IEEE, 2021.

Abstract

Though machine learning algorithms are able to achieve pattern recognition from the correlation between data and labels, the presence of spurious features in the data decreases the robustness of these learned relationships with respect to varied testing environments. This is known as out-of-distribution (OoD) generalization problem. Recently, invariant risk minimization (IRM) attempts to tackle this issue by penalizing predictions based on the unstable spurious features in the data collected from different environments. However, similar to domain adaptation or domain generalization, a prevalent non-trivial limitation in these works is that the environment information is assigned by human specialists, i.e. a priori, or determined heuristically. However, an inappropriate group partitioning can dramatically deteriorate the OoD generalization and this process is expensive and time-consuming. To deal with this issue, we propose a novel theoretically principled min-max framework to iteratively construct a worst-case splitting, i.e. creating the most challenging environment splittings for the backbone learning paradigm (e.g. IRM) to learn the robust feature representation. We also design a differentiable training strategy to facilitate the feasible gradient- based computation. Numerical experiments show that our algorithmic framework has achieved superior and stable performance in various datasets, such as Colored MNIST and Punctuated Stanford sentiment treebank (SST). Furthermore, we also find our algorithm to be robust even to a strong data poisoning attack. To the best of our knowledge, this is one of the first to adopt differentiable environment splitting method to enable stable predictions across environments without environment index information, which achieves the state-of-the-art performance on datasets with strong spurious correlation, such as Colored MNIST.

Details

Database :
OpenAIRE
Journal :
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Accession number :
edsair.doi...........3b25d01ed046552275a3f80778de23fa
Full Text :
https://doi.org/10.1109/cvpr46437.2021.01226