Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
This work addresses robust generalization for few-shot learning, which is incremental as it builds on existing Sinkhorn DRO methods by making them more adaptable.
The paper tackles the problem of robust generalization in few-shot learning under distribution shifts by proposing a Prototype-Guided Distributionally Robust Optimization (PG-DRO) framework that learns class-adaptive priors from base data. It shows that PG-DRO outperforms standard learners and DRO baselines in few-shot scenarios.
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.