提出HAMR框架，自适应解决文本分类中的类别不平衡问题。
Model-Agnostic Meta Learning for Class Imbalance Adaptation
- 通过双层优化动态分配样本权重，聚焦难例和少数类
- 在6个数据集上显著提升少数类性能，超越多个强基线
- 适合处理医疗、灾情、情感等领域的不平衡文本任务
类别不平衡是NLP任务中普遍存在的挑战，严重影响跨领域和应用的鲁棒性表现。我们提出一种统一框架HAMR（Hardness-Aware Meta-Resample），可自适应地同时应对类别不平衡与数据难度。HAMR采用双层优化机制，动态估计实例级权重，优先关注真正困难的样本和少数类别；同时引入邻域感知重采样机制，增强对难例及其语义相似邻居的关注。我们在涵盖生物医学、灾情响应、情感分析等多个领域的六个不平衡数据集上验证了HAMR的有效性。实验结果表明，该方法显著提升了少数类的性能，并持续优于多个强基线模型。大量消融实验进一步证明，所提出的模块协同作用带来性能提升，凸显HAMR在类别不平衡适应上的灵活性与泛化能力。代码已公开于https://github.com/trust-nlp/ImbalanceLearning。
原文摘要 · Abstract (English)
Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty. HAMR employs bi-level optimizations to dynamically estimate instance-level weights that prioritize genuinely challenging samples and minority classes, while a neighborhood-aware resampling mechanism amplifies training focus on hard examples and their semantically similar neighbors. We validate HAMR on six imbalanced datasets covering multiple tasks and spanning biomedical, disaster response, and sentiment domains. Experimental results show that HAMR achieves substantial improvements for minority classes and consistently outperforms strong baselines. Extensive ablation studies demonstrate that our proposed modules synergistically contribute to performance gains and highlight HAMR as a flexible and generalizable approach for class imbalance adaptation. Code is available at https://github.com/trust-nlp/ImbalanceLearning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。