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 the 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. We show that our proposed approach is closely related to the well-known Information Bottleneck (IB) framework and prove that under certain assumptions, entropy minimization can exactly recover the true invariant features. Our approach provides competitive classification accuracy compared to recent theoretically-principled state-of-the-art alternatives across several DG datasets.
翻译:最近出现了一些有希望的通用域法(DG),尽管理论很有希望,但这类方法在共同的分类任务中却未能成功,因为其中混合了真实的不变特征和虚假的变数特征。为了解决这个问题,我们提议了一个基于有条件的最小化(CEM)原则的框架,以过滤虚假的变数特征,从而形成一种具有更好概括能力的新的算法。我们表明,我们提出的方法与众所周知的信息瓶颈(IB)框架密切相关,并证明在某些假设下,最小化的酶完全可以恢复真实的变数特征。我们的方法提供了与最近若干DG数据集中具有理论原理的、最先进的替代方法相比,具有竞争性的分类准确性。