用多样原型集成提升模型对子群体偏移的鲁棒性
Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
- 用多个聚焦不同特征的原型分类器组成集成
- 在9个真实数据集上最差组准确率超越现有方法
- 无需子群体标签，适合标注缺失场景
子群体偏移指训练集与目标集间子群体分布不一致，严重降低模型性能。现有方法依赖重加权策略，但需预设子群体数量与成员标签，难以适用于多数真实数据集。本文提出多样原型集成（DPE），将标准线性分类层替换为多个原型分类器的混合结构，每个分类器专注于不同特征与样本，实现自适应风险捕捉。在涵盖多种领域和偏移类型的9个真实数据集上进行实证评估，DPE在最差组准确率方面常优于当前最优方法。代码已开源。
原文摘要 · Abstract (English)
The subpopulationtion shift, characterized by a disparity in subpopulation distributibetween theween the training and target datasets, can significantly degrade the performance of machine learning models. Current solutions to subpopulation shift involve modifying empirical risk minimization with re-weighting strategies to improve generalization. This strategy relies on assumptions about the number and nature of subpopulations and annotations on group membership, which are unavailable for many real-world datasets. Instead, we propose using an ensemble of diverse classifiers to adaptively capture risk associated with subpopulations. Given a feature extractor network, we replace its standard linear classification layer with a mixture of prototypical classifiers, where each member is trained to classify the data while focusing on different features and samples from other members. In empirical evaluation on nine real-world datasets, covering diverse domains and kinds of subpopulation shift, our method of Diverse Prototypical Ensembles (DPEs) often outperforms the prior state-of-the-art in worst-group accuracy. The code is available at https://github.com/minhto2802/dpe4subpop
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。