arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.00629cs.LG
收藏

一种领域泛化中模型验证的原则性方法

A principled approach to model validation in domain generalization

Tufts University(塔夫茨大学);Boston University(波士顿大学)

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

AI总结:

针对领域泛化中模型选择仅依赖分类风险的问题,本文理论证明了分类风险与领域差异间的权衡,提出一种兼顾两者的新颖模型选择方法,并在多个数据集上验证了其有效性。

摘要:

领域泛化旨在学习具有良好泛化能力的模型,即所学模型不仅应在若干已见领域上表现良好,还应在具有不同数据分布的未见领域上表现良好。最先进的领域泛化方法通常联合训练表示函数和分类器,以最小化分类风险和领域差异。然而,在模型选择方面,这些方法大多依赖传统验证程序,仅根据验证集上最低的分类风险来选择模型。在本文中,我们从理论上证明了最小化分类风险与缓解领域差异之间存在权衡,即不可能同时实现这两个目标的最小化。受此理论结果启发,我们提出了一种新颖的模型选择方法,建议验证过程应同时考虑分类风险和领域差异。我们通过在多个领域泛化数据集上的数值结果验证了所提方法的有效性。

英文摘要:

Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions. State-of-the-art domain generalization methods typically train a representation function followed by a classifier jointly to minimize both the classification risk and the domain discrepancy. However, when it comes to model selection, most of these methods rely on traditional validation routines that select models solely based on the lowest classification risk on the validation set. In this paper, we theoretically demonstrate a trade-off between minimizing classification risk and mitigating domain discrepancy, i.e., it is impossible to achieve the minimum of these two objectives simultaneously. Motivated by this theoretical result, we propose a novel model selection method suggesting that the validation process should account for both the classification risk and the domain discrepancy. We validate the effectiveness of the proposed method by numerical results on several domain generalization datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑