Scholarlink

<p>Cross-domain text classification (CDTC) is applied to improve the performance of models trained on source domains when applied to a target domain, but often rely heavily on domain specificity. Domain generalization (DG) is considered as a good solution. In this work, we explore and construct a unified text DG framework UAM-CFEO to improve the performance and generalization of CDTC. Specifically, UAM-CFEO incorporates a module and a two-stage feature optimization and enhancement strategy. Specifically, CAE (Causal AutoEncoder) module is designed to extract cross-domain stable causal features. The first-stage feature optimization strategy is introduced to combine causal invariant learning with supervised contrastive learning for enhancing both the consistency and discriminability of causal representations across domains. Then, we augment the extracted causal features with a key-value memory augmentation that trained with an uncertainty-aware meta-learning framework in the second enhancement stage, so as to improve the robustness under low-resource settings and large distribution shifts. Meanwhile, Extensive experiments demonstrate that UAM-CFEO consistently outperforms existing methods in both multi-domain leave-one-domain-out settings and cross-dataset evaluations, validating its effectiveness and superiority.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

UAM-CFEO: causal feature extraction and optimization for cross-domain text classification with uncertainty-aware memory augmentation

  • 期刊论文

  • 发表日期：

    2026年7月14日

查看全文
  • Yirong Zhang,
  • Rong Yan,
  • Yaozhang Han

摘要

Cross-domain text classification (CDTC) is applied to improve the performance of models trained on source domains when applied to a target domain, but often rely heavily on domain specificity. Domain generalization (DG) is considered as a good solution. In this work, we explore and construct a unified text DG framework UAM-CFEO to improve the performance and generalization of CDTC. Specifically, UAM-CFEO incorporates a module and a two-stage feature optimization and enhancement strategy. Specifically, CAE (Causal AutoEncoder) module is designed to extract cross-domain stable causal features. The first-stage feature optimization strategy is introduced to combine causal invariant learning with supervised contrastive learning for enhancing both the consistency and discriminability of causal representations across domains. Then, we augment the extracted causal features with a key-value memory augmentation that trained with an uncertainty-aware meta-learning framework in the second enhancement stage, so as to improve the robustness under low-resource settings and large distribution shifts. Meanwhile, Extensive experiments demonstrate that UAM-CFEO consistently outperforms existing methods in both multi-domain leave-one-domain-out settings and cross-dataset evaluations, validating its effectiveness and superiority.