Towards Principled Disentanglement for Domain Generalization
This addresses the problem of machine learning models generalizing to unseen data for researchers and practitioners, but it appears incremental as it builds on existing disentanglement and domain generalization methods.
The paper tackles out-of-distribution generalization by formalizing it as a constrained optimization problem called Disentanglement-constrained Domain Generalization (DDG), proposing a primal-dual algorithm that learns disentangled semantic and variation encoders, and achieves competitive performance on benchmarks.
A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG). We relax this non-trivial constrained optimization problem to a tractable form with finite-dimensional parameterization and empirical approximation. Then a theoretical analysis of the extent to which the above transformations deviates from the original problem is provided. Based on the transformation, we propose a primal-dual algorithm for joint representation disentanglement and domain generalization. In contrast to traditional approaches based on domain adversarial training and domain labels, DDG jointly learns semantic and variation encoders for disentanglement, enabling flexible manipulation and augmentation on training data. DDG aims to learn intrinsic representations of semantic concepts that are invariant to nuisance factors and generalizable across domains. Comprehensive experiments on popular benchmarks show that DDG can achieve competitive OOD performance and uncover interpretable salient structures within data.