用自适应先验提升少样本下的鲁棒泛化能力
Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
- 通过层次最优传输学习类别自适应先验
- 在少样本场景下显著提升鲁棒性，优于标准方法和DRO基线
- 适合需要强泛化能力的少样本学习任务
少样本学习要求模型在监督信息有限的情况下仍具备泛化能力，并对分布偏移保持鲁棒性。现有基于Sinkhorn的分布鲁棒优化（DRO）方法虽有理论保证，但依赖固定参考分布，适应性受限。本文提出原型引导的分布鲁棒优化（PG-DRO）框架，通过层次最优传输从大量基础数据中学习类别自适应先验，并将其嵌入到Sinkhorn DRO公式中。该设计使少样本信息自然融入生成类特定鲁棒决策的过程，兼具理论依据与高效性，同时使不确定集与可迁移结构知识对齐。实验表明，PG-DRO在少样本场景下实现了更强的鲁棒泛化能力，优于标准学习器和DRO基线。
原文摘要 · Abstract (English)
Few-shot learning requires models to generalize under limited supervision while remaining robust to distribution shifts. Existing Sinkhorn Distributionally Robust Optimization (DRO) methods provide theoretical guarantees but rely on a fixed reference distribution, which limits their adaptability. We propose a Prototype-Guided Distributionally Robust Optimization (PG-DRO) framework that learns class-adaptive priors from abundant base data via hierarchical optimal transport and embeds them into the Sinkhorn DRO formulation. This design enables few-shot information to be organically integrated into producing class-specific robust decisions that are both theoretically grounded and efficient, and further aligns the uncertainty set with transferable structural knowledge. Experiments show that PG-DRO achieves stronger robust generalization in few-shot scenarios, outperforming both standard learners and DRO baselines.
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。