基于自适应最优传输先验的鲁棒泛化决策聚焦学习
Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
AI总结：
本文提出PG-DRO框架，通过自适应最优传输学习类适应性先验，提升少样本学习的鲁棒泛化能力。
摘要：
少样本学习要求模型在有限监督下进行泛化，同时保持对分布偏移的鲁棒性。现有Sinkhorn分布鲁棒优化（DRO）方法提供理论保证，但依赖固定参考分布，限制了其适应性。我们提出了一种原型引导的分布鲁棒优化（PG-DRO）框架，通过层次最优传输从丰富的基础数据中学习类适应性先验，并将其嵌入Sinkhorn DRO公式中。这种设计使少样本信息能够有机地整合到生成类特定鲁棒决策中，既理论严谨又高效，并进一步将不确定性集与可转移的结构知识对齐。实验表明，PG-DRO在少样本场景中实现了更强的鲁棒泛化，优于标准学习者和DRO基线。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
