医学影像中实现层次化多标签的合理拒答，避免逻辑矛盾。
Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
- 设计层次化拒答机制，确保拒绝决策符合临床分类逻辑。
- 提出精确投影与递归策略优化方法，使拒答错误率趋近于零。
- 适用于需要专家协作的医疗影像分析场景，提升系统可信度。
学习拒答（L2D）使模型可自主预测或转交专家，但以往工作多假设标签空间为扁平结构。本文首次研究具有层次化多标签决策的L2D设置，源于医学影像中发现结果按临床分类组织的现实流程。在该场景下，拒答是委托行为而非标签分配，若将各标签的拒答视为独立决策，会导致拒答不一致，包括分类矛盾、委托违规以及对模型自身已判定标签的重复拒答。本文在选择-排除移交契约下形式化了协同层次拒答，刻画了贝叶斯最优协同拒答规则，并证明即使节点级贝叶斯L2D也可能导致行动不一致。随后提出两种修复方案：精确协同投影（动态规划解码器），以及结合递归策略优化的分类信念传播（TBP+RPO）联合动作模型，其训练与推理使用相同递归结构。在真实医生与受控专家的医学影像基准测试中，朴素二元相关L2D表现出显著不一致性；投影可完全消除该问题，而快速的TBP+RPO将不一致性降至接近零，同时保持强实用性。
原文摘要 · Abstract (English)
Learning to Defer (L2D) enables a model to predict autonomously or defer to an expert, but prior work largely assumes flat label spaces. We study the first L2D setting with hierarchical multi-label decisions, motivated by medical-imaging workflows in which findings are organised by clinical taxonomies. In this setting, deferral is a delegation action rather than a label assignment, so treating it as an independent per-label decision can produce deferral incoherence, including taxonomic contradictions, delegation violations, and deferrals of labels already implied by the model's own assertions. We formalise coherent hierarchical deferral under a Selective-Exclusion handoff contract, characterise the Bayes-optimal coherent deferral rule, and show that even nodewise Bayes L2D can be action-incoherent. We then propose two remedies: exact coherent projection, a dynamic-programming decoder over the coherent action set, and Taxonomic Belief Propagation (TBP) with Recursive Policy Optimisation (RPO), a contract-aware joint action model trained through the same recursion used at inference. Across real-reader and controlled-expert medical-imaging benchmarks, naive binary-relevance L2D exhibits non-trivial incoherence. Projection removes it exactly, and fast TBP+RPO drives incoherence near zero while retaining strong utility.
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。