Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain generalization, where a model is trained on one source domain and tested on multiple target domains that are unseen during training. We propose IMO: Invariant features Masks for Out-of-Distribution text classification, to achieve OOD generalization by learning invariant features. During training, IMO would learn sparse mask layers to remove irrelevant features for prediction, where the remaining features keep invariant. Additionally, IMO has an attention module at the token level to focus on tokens that are useful for prediction. Our comprehensive experiments show that IMO substantially outperforms strong baselines in terms of various evaluation metrics and settings.

该研究关注域泛化的特定问题，通过学习不变特征，提出了IMO：用于超出领域文本分类的不变特征掩码，来实现域外泛化；此外，IMO还具有注意力模块，用于关注对预测有用的令牌。综合实验证明，IMO在各种评估指标和设置方面显著优于强基准算法。

IMO: 基于贪心逐层稀疏表示学习的预训练模型用于超出分布的文本分类