In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between the seen domains for a better performance on the unseen domain. While the proposed approach can be implemented via an arbitrary combination of covariate-alignment and concept-alignment modules, in this work we use well-established approaches for distributional alignment namely, Maximum Mean Discrepancy (MMD) and covariance Alignment (CORAL), and use an Invariant Risk Minimization (IRM)-based approach for concept alignment. Our numerical results show that the proposed methods perform as well as or better than the state-of-the-art for domain generalization on several data sets.
@article{arxiv.2208.00898,
title = {Joint covariate-alignment and concept-alignment: a framework for domain generalization},
author = {Thuan Nguyen and Boyang Lyu and Prakash Ishwar and Matthias Scheutz and Shuchin Aeron},
journal= {arXiv preprint arXiv:2208.00898},
year = {2022}
}
Comments
8 pages, 2 figures, and 1 table. This paper is accepted at 32nd IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2022)