提出多任务学习的两阶段拒答框架，统一处理分类与回归。
A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
- 设计统一拒答机制，联合优化分类与回归任务。
- 理论证明方法收敛至最优拒答策略，且具一致性保证。
- 适用于医疗、目标检测等需同时处理多类任务的场景。
两阶段学习拒答（L2D）框架在分类和回归任务中已有广泛研究，但现实应用常需在多任务设置下同时解决分类与回归问题。本文提出一种新型两阶段L2D框架用于多任务学习，通过统一的拒答机制整合分类与回归任务。所提方法采用双阶段代理损失族，我们证明其贝叶斯一致且$(\mathcal{G}, \mathcal{R})$-一致，确保收敛至贝叶斯最优拒答器。推导了与交叉熵代理损失及代理成本$ L_1 $-范数相关的显式一致性界，并将可最小化间隙分析扩展至多专家两阶段情形。还明确揭示了共享表示学习对这些一致性保证的影响。在目标检测与电子健康记录分析上的实验验证了方法的有效性，并凸显了现有L2D方法在多任务场景下的局限性。
原文摘要 · Abstract (English)
The Two-Stage Learning-to-Defer (L2D) framework has been extensively studied for classification and, more recently, regression tasks. However, many real-world applications require solving both tasks jointly in a multi-task setting. We introduce a novel Two-Stage L2D framework for multi-task learning that integrates classification and regression through a unified deferral mechanism. Our method leverages a two-stage surrogate loss family, which we prove to be both Bayes-consistent and $(\mathcal{G}, \mathcal{R})$-consistent, ensuring convergence to the Bayes-optimal rejector. We derive explicit consistency bounds tied to the cross-entropy surrogate and the $L_1$-norm of agent-specific costs, and extend minimizability gap analysis to the multi-expert two-stage regime. We also make explicit how shared representation learning -- commonly used in multi-task models -- affects these consistency guarantees. Experiments on object detection and electronic health record analysis demonstrate the effectiveness of our approach and highlight the limitations of existing L2D methods in multi-task scenarios.
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。