Conditional entropy minimization principle for learning domain invariant representation features

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG). Despite promising theory, such approaches fail in common classification tasks due to mixing of "true invariant features" and "spurious invariant features". To address this, we propose a framework based on the conditional entropy minimization (CEM) principle to filter-out the spurious invariant features leading to a new algorithm with a better generalization capability.

@inproceedings{nguyenetal2022icpr,
  title={Conditional entropy minimization principle for learning domain invariant representation features},
  author={Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron},
  year={2022},
  booktitle={International Conference on Pattern Recognition},
  url={https://hrilab.tufts.edu/publications/nguyenetal2022icpr.pdf}
}